feat(skills): simplify-code v1.1.0 — altitude reviewer, inline fallback, upstream /simplify parity - #70440
Merged
Merged
Conversation
alt-glitch
added
type/feature
Contributor
…ion (4th altitude reviewer, inline fallback) Claude Code's /simplify was renamed away, community-restored, and rebuilt since our 3-agent port (v2.1.63 -> v2.1.154+). This brings simplify-code in line with the current upstream design, re-expressed in our own wording and layered onto our existing risk-tier/confidence machinery: - New Reviewer 4 (Altitude): flags band-aid fixes layered on shared infrastructure — special cases, symptom patches with unfixed sibling sites, workaround stacks — and points at the deeper mechanism fix. Matches our AGENTS.md 'fix the class, not the site' rubric. - Explicit cleanup-vs-bug-hunt boundary: this skill improves working code; correctness review stays with requesting-code-review. - Inline single-pass fallback when delegate_task is unavailable (leaf subagents, delegation disabled) — previously the skill just broke; now all four angles run sequentially with honest disclosure. - Finding format gains a concrete-cost field. - Efficiency reviewer adds closure-capture scope-retention leaks. - Pitfalls: fan-out cap 3 -> 4, band-aid-vs-deliberate-boundary caveat, no-bug-hunting drift guard. Kept our value-adds upstream lacks: SAFE/CAREFUL/RISKY tiers, Chesterton's Fence via git blame, dry-run/focus/scope modifiers.
teknium1
force-pushed
the
hermes/hermes-33fd2a15
branch
from
July 24, 2026 02:47
cbd515c to
d9a2acb
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Updates the bundled
simplify-codeskill (v1.0.0 → v1.1.0) to track how Claude Code's/simplifyevolved since our February-era port — most importantly adding the fourth Altitude reviewer and an inline no-delegation fallback. All prose is our own wording, concept-inspired from public changelog/docs descriptions, not copied.Upstream timeline that motivated this (from the public Claude Code changelog):
/simplifyadded — 3 parallel agents (reuse, quality, efficiency). This is what we ported./code-review, became a correctness bug-hunter; cleanup behavior removed./simplifyrestored as cleanup-only after community pushback ([FEATURE] Bring back /simplify anthropics/claude-code#61581), now with 4 angles: reuse, simplification, efficiency, altitude.Changes
skills/software-development/simplify-code/SKILL.md:requesting-code-review. New pitfall guards against drift.delegate_taskisn't available (leaf subagent, delegation disabled, budget exhausted), run all four angles sequentially in-context and disclose that in the summary — previously the skill had no answer for this and simply broke.website/docs/user-guide/skills/bundled/software-development/software-development-simplify-code.md: regenerated viawebsite/scripts/generate-skill-docs.py.website/docs/reference/skills-catalog.md: description row updated (3-agent → 4-agent).IP note
The updated prompts were written fresh in our own words from the concepts described in Anthropic's public changelog and community reports. Verified zero 8-word-shingle overlap against the upstream prompt texts.
Validation
scripts/run_tests.sh tests/skills/ -qtools.skills_sync.sync_skills()into tempHERMES_HOMEInfographic