feat(prompt): point agent at hermes-agent skill + docs site for Hermes questions - #16535
Merged
Conversation
Contributor
🚨 CRITICAL Supply Chain Risk DetectedThis PR contains a pattern that has been used in real supply chain attacks. A maintainer must review the flagged code carefully before merging. 🚨 CRITICAL: Install-hook file added or modifiedThese files can execute code during package installation or interpreter startup. Files: Scanner only fires on high-signal indicators: .pth files, base64+exec/eval combos, subprocess with encoded commands, or install-hook files. Low-signal warnings were removed intentionally — if you're seeing this comment, the finding is worth inspecting. |
alt-glitch
added
type/feature
…s questions Adds a short always-on pointer to the system prompt: when the user asks about configuring, setting up, troubleshooting, or using Hermes Agent itself, load the hermes-agent skill via skill_view(name='hermes-agent') and fall back to https://hermes-agent.nousresearch.com/docs via web_extract. Keeps sessions without skill_view loaded useful too — the docs URL + web_extract is enough to answer most questions. The guidance is appended right after DEFAULT_AGENT_IDENTITY (or SOUL.md) so it ships regardless of which toolset profile is active. Footprint is ~560 chars, behind the existing prompt cache.
teknium1
force-pushed
the
hermes/hermes-17227233
branch
from
April 27, 2026 12:35
7652f9d to
b544cab
Compare
Contributor
🚨 CRITICAL Supply Chain Risk DetectedThis PR contains a pattern that has been used in real supply chain attacks. A maintainer must review the flagged code carefully before merging. 🚨 CRITICAL: Install-hook file added or modifiedThese files can execute code during package installation or interpreter startup. Files: Scanner only fires on high-signal indicators: .pth files, base64+exec/eval combos, subprocess with encoded commands, or install-hook files. Low-signal warnings were removed intentionally — if you're seeing this comment, the finding is worth inspecting. |
cluricaun28
referenced
this pull request
in cluricaun28/Logos
Apr 28, 2026
…s questions (#16535) Adds a short always-on pointer to the system prompt: when the user asks about configuring, setting up, troubleshooting, or using Hermes Agent itself, load the hermes-agent skill via skill_view(name='hermes-agent') and fall back to https://hermes-agent.nousresearch.com/docs via web_extract. Keeps sessions without skill_view loaded useful too — the docs URL + web_extract is enough to answer most questions. The guidance is appended right after DEFAULT_AGENT_IDENTITY (or SOUL.md) so it ships regardless of which toolset profile is active. Footprint is ~560 chars, behind the existing prompt cache.
donald131
pushed a commit
to donald131/hermes-agent
that referenced
this pull request
May 2, 2026
…s questions (NousResearch#16535) Adds a short always-on pointer to the system prompt: when the user asks about configuring, setting up, troubleshooting, or using Hermes Agent itself, load the hermes-agent skill via skill_view(name='hermes-agent') and fall back to https://hermes-agent.nousresearch.com/docs via web_extract. Keeps sessions without skill_view loaded useful too — the docs URL + web_extract is enough to answer most questions. The guidance is appended right after DEFAULT_AGENT_IDENTITY (or SOUL.md) so it ships regardless of which toolset profile is active. Footprint is ~560 chars, behind the existing prompt cache.
02356abc
pushed a commit
to 02356abc/hermes-agent
that referenced
this pull request
May 14, 2026
…s questions (NousResearch#16535) Adds a short always-on pointer to the system prompt: when the user asks about configuring, setting up, troubleshooting, or using Hermes Agent itself, load the hermes-agent skill via skill_view(name='hermes-agent') and fall back to https://hermes-agent.nousresearch.com/docs via web_extract. Keeps sessions without skill_view loaded useful too — the docs URL + web_extract is enough to answer most questions. The guidance is appended right after DEFAULT_AGENT_IDENTITY (or SOUL.md) so it ships regardless of which toolset profile is active. Footprint is ~560 chars, behind the existing prompt cache.
dannyJ848
pushed a commit
to dannyJ848/hermes-agent
that referenced
this pull request
May 17, 2026
…s questions (NousResearch#16535) Adds a short always-on pointer to the system prompt: when the user asks about configuring, setting up, troubleshooting, or using Hermes Agent itself, load the hermes-agent skill via skill_view(name='hermes-agent') and fall back to https://hermes-agent.nousresearch.com/docs via web_extract. Keeps sessions without skill_view loaded useful too — the docs URL + web_extract is enough to answer most questions. The guidance is appended right after DEFAULT_AGENT_IDENTITY (or SOUL.md) so it ships regardless of which toolset profile is active. Footprint is ~560 chars, behind the existing prompt cache.
gweeteve
pushed a commit
to gweeteve/hermes-agent
that referenced
this pull request
Jun 2, 2026
…s questions (NousResearch#16535) Adds a short always-on pointer to the system prompt: when the user asks about configuring, setting up, troubleshooting, or using Hermes Agent itself, load the hermes-agent skill via skill_view(name='hermes-agent') and fall back to https://hermes-agent.nousresearch.com/docs via web_extract. Keeps sessions without skill_view loaded useful too — the docs URL + web_extract is enough to answer most questions. The guidance is appended right after DEFAULT_AGENT_IDENTITY (or SOUL.md) so it ships regardless of which toolset profile is active. Footprint is ~560 chars, behind the existing prompt cache.
teknium1
added a commit
that referenced
this pull request
Jun 4, 2026
…38538) The HERMES_AGENT_HELP_GUIDANCE block (added #16535) only fired when the user explicitly asked about configuring/setting up Hermes. Broaden it so the agent treats the docs as a standing source of self-knowledge for any Hermes-related help and for understanding its own features/tools, points to the hermes-agent skill for additional guidance, and treats the docs as the authoritative/latest source of truth when the two differ. Static constant in the cache-safe stable tier — no prompt-cache impact.
Yuki-14544869
pushed a commit
to Yuki-14544869/hermes-agent
that referenced
this pull request
Jun 4, 2026
…ousResearch#38538) The HERMES_AGENT_HELP_GUIDANCE block (added NousResearch#16535) only fired when the user explicitly asked about configuring/setting up Hermes. Broaden it so the agent treats the docs as a standing source of self-knowledge for any Hermes-related help and for understanding its own features/tools, points to the hermes-agent skill for additional guidance, and treats the docs as the authoritative/latest source of truth when the two differ. Static constant in the cache-safe stable tier — no prompt-cache impact.
davidgut1982
pushed a commit
to davidgut1982/hermes-agent
that referenced
this pull request
Jun 5, 2026
…ousResearch#38538) The HERMES_AGENT_HELP_GUIDANCE block (added NousResearch#16535) only fired when the user explicitly asked about configuring/setting up Hermes. Broaden it so the agent treats the docs as a standing source of self-knowledge for any Hermes-related help and for understanding its own features/tools, points to the hermes-agent skill for additional guidance, and treats the docs as the authoritative/latest source of truth when the two differ. Static constant in the cache-safe stable tier — no prompt-cache impact.
changman
pushed a commit
to changman/hermes-agent
that referenced
this pull request
Jun 10, 2026
…ousResearch#38538) The HERMES_AGENT_HELP_GUIDANCE block (added NousResearch#16535) only fired when the user explicitly asked about configuring/setting up Hermes. Broaden it so the agent treats the docs as a standing source of self-knowledge for any Hermes-related help and for understanding its own features/tools, points to the hermes-agent skill for additional guidance, and treats the docs as the authoritative/latest source of truth when the two differ. Static constant in the cache-safe stable tier — no prompt-cache impact.
alt-glitch
pushed a commit
that referenced
this pull request
Jun 14, 2026
…38538) The HERMES_AGENT_HELP_GUIDANCE block (added #16535) only fired when the user explicitly asked about configuring/setting up Hermes. Broaden it so the agent treats the docs as a standing source of self-knowledge for any Hermes-related help and for understanding its own features/tools, points to the hermes-agent skill for additional guidance, and treats the docs as the authoritative/latest source of truth when the two differ. Static constant in the cache-safe stable tier — no prompt-cache impact.
kossteg
pushed a commit
to kossteg/hermes-agent
that referenced
this pull request
Jun 16, 2026
…ousResearch#38538) The HERMES_AGENT_HELP_GUIDANCE block (added NousResearch#16535) only fired when the user explicitly asked about configuring/setting up Hermes. Broaden it so the agent treats the docs as a standing source of self-knowledge for any Hermes-related help and for understanding its own features/tools, points to the hermes-agent skill for additional guidance, and treats the docs as the authoritative/latest source of truth when the two differ. Static constant in the cache-safe stable tier — no prompt-cache impact.
T02200059
pushed a commit
to T02200059/hermes-agent
that referenced
this pull request
Jun 18, 2026
…ousResearch#38538) The HERMES_AGENT_HELP_GUIDANCE block (added NousResearch#16535) only fired when the user explicitly asked about configuring/setting up Hermes. Broaden it so the agent treats the docs as a standing source of self-knowledge for any Hermes-related help and for understanding its own features/tools, points to the hermes-agent skill for additional guidance, and treats the docs as the authoritative/latest source of truth when the two differ. Static constant in the cache-safe stable tier — no prompt-cache impact.
xyshanren
pushed a commit
to xyshanren/hermes-agent-cn
that referenced
this pull request
Jun 25, 2026
…ousResearch#38538) The HERMES_AGENT_HELP_GUIDANCE block (added NousResearch#16535) only fired when the user explicitly asked about configuring/setting up Hermes. Broaden it so the agent treats the docs as a standing source of self-knowledge for any Hermes-related help and for understanding its own features/tools, points to the hermes-agent skill for additional guidance, and treats the docs as the authoritative/latest source of truth when the two differ. Static constant in the cache-safe stable tier — no prompt-cache impact.
waefrebeorn
pushed a commit
to waefrebeorn/slermes
that referenced
this pull request
Jul 2, 2026
…s questions (NousResearch#16535) Adds a short always-on pointer to the system prompt: when the user asks about configuring, setting up, troubleshooting, or using Hermes Agent itself, load the hermes-agent skill via skill_view(name='hermes-agent') and fall back to https://hermes-agent.nousresearch.com/docs via web_extract. Keeps sessions without skill_view loaded useful too — the docs URL + web_extract is enough to answer most questions. The guidance is appended right after DEFAULT_AGENT_IDENTITY (or SOUL.md) so it ships regardless of which toolset profile is active. Footprint is ~560 chars, behind the existing prompt cache.
waefrebeorn
pushed a commit
to waefrebeorn/slermes
that referenced
this pull request
Jul 2, 2026
…ousResearch#38538) The HERMES_AGENT_HELP_GUIDANCE block (added NousResearch#16535) only fired when the user explicitly asked about configuring/setting up Hermes. Broaden it so the agent treats the docs as a standing source of self-knowledge for any Hermes-related help and for understanding its own features/tools, points to the hermes-agent skill for additional guidance, and treats the docs as the authoritative/latest source of truth when the two differ. Static constant in the cache-safe stable tier — no prompt-cache impact.
santhreal
pushed a commit
to santhreal/hermes-agent
that referenced
this pull request
Jul 13, 2026
…ousResearch#38538) The HERMES_AGENT_HELP_GUIDANCE block (added NousResearch#16535) only fired when the user explicitly asked about configuring/setting up Hermes. Broaden it so the agent treats the docs as a standing source of self-knowledge for any Hermes-related help and for understanding its own features/tools, points to the hermes-agent skill for additional guidance, and treats the docs as the authoritative/latest source of truth when the two differ. Static constant in the cache-safe stable tier — no prompt-cache impact.
donbowman
pushed a commit
to donbowman/hermes-agent
that referenced
this pull request
Jul 13, 2026
…ousResearch#38538) The HERMES_AGENT_HELP_GUIDANCE block (added NousResearch#16535) only fired when the user explicitly asked about configuring/setting up Hermes. Broaden it so the agent treats the docs as a standing source of self-knowledge for any Hermes-related help and for understanding its own features/tools, points to the hermes-agent skill for additional guidance, and treats the docs as the authoritative/latest source of truth when the two differ. Static constant in the cache-safe stable tier — no prompt-cache impact.
Gravezzz
pushed a commit
to Gravezzz/hermes-agent
that referenced
this pull request
Jul 21, 2026
…ousResearch#38538) The HERMES_AGENT_HELP_GUIDANCE block (added NousResearch#16535) only fired when the user explicitly asked about configuring/setting up Hermes. Broaden it so the agent treats the docs as a standing source of self-knowledge for any Hermes-related help and for understanding its own features/tools, points to the hermes-agent skill for additional guidance, and treats the docs as the authoritative/latest source of truth when the two differ. Static constant in the cache-safe stable tier — no prompt-cache impact.
leewenjie
pushed a commit
to leewenjie/hermes-agent
that referenced
this pull request
Aug 7, 2026
…ousResearch#38538) The HERMES_AGENT_HELP_GUIDANCE block (added NousResearch#16535) only fired when the user explicitly asked about configuring/setting up Hermes. Broaden it so the agent treats the docs as a standing source of self-knowledge for any Hermes-related help and for understanding its own features/tools, points to the hermes-agent skill for additional guidance, and treats the docs as the authoritative/latest source of truth when the two differ. Static constant in the cache-safe stable tier — no prompt-cache impact.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Teaches the agent to load the
hermes-agentskill and cite https://hermes-agent.nousresearch.com/docs when users ask about configuring, setting up, or using Hermes Agent itself. Previously the agent would answer from general knowledge or invent paths — neither grounded in the actual docs nor the bundled skill.Changes
agent/prompt_builder.py: newHERMES_AGENT_HELP_GUIDANCEconstant (~560 chars).run_agent.py: append it to the system prompt right after identity (or SOUL.md) in_build_system_prompt(), before tool-aware guidance.Not tool-gated: the docs URL +
web_extractis useful even withoutskill_viewin the active toolset; whenskill_viewis loaded the agent gets the richer path.Validation
skill_view(name='hermes-agent')+ docs URLtests/agent/test_prompt_builder.pytests/run_agent/Verified end-to-end via
execute_code: the guidance lands in the assembled system prompt (both docs URL andskill_viewhint present).