refactor(skills): sweep agent-agnostic phrasing across Tier-1/featured#40
Merged
naimkatiman merged 1 commit intomainfrom Apr 28, 2026
Merged
Conversation
Replace Claude-specific phrasing with neutral "agent" terminology across gateguard, token-budget-advisor, verification-loop, strategic-compact, and the source skills README so these skills are invocable from any AI coding agent (Claude, Codex, Gemini, etc.). Source files (5) + plugin mirror (5, regenerated via npm run build). Phrasing-only refactor; no behavior change. 238/238 tests pass. Out of scope: - proceed-with-the-recommendation (covered by PR #38) - workspace-surface-audit (most matches are legitimate product references; deferred to a separate audit) - ralph (both Claude references are legitimate: section header for Claude Code usage and the literal scripts/ralph/CLAUDE.md path) - token-budget-advisor.md attribution line ("Token Budget Advisor for Claude Code" is the original project name)
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request updates several documentation files and skill descriptions to replace specific references to "Claude" and "Claude Code" with more generic terminology such as "agent" and "agent coding sessions." A review comment identifies a minor phrasing inconsistency in skills/README.md and provides a suggestion to use "agent" as an adjective for better alignment with the rest of the changes.
| | Skill | What it does | Source | | ||
| |-------|--------------|--------| | ||
| | **`proceed-with-the-recommendation`** ⭐ | Walks any Claude recommendation list top-to-bottom under the 7 Laws — routes each item to the right specialist (`superpowers:*`, `ralph`, `workspace-surface-audit`, `simplify`, `security-review`, `schedule`, `loop`), falls back to inline behavior when a specialist isn't installed, verifies per item, halts on `needs-approval` | @naimkatiman | | ||
| | **`proceed-with-the-recommendation`** ⭐ | Walks any agent's recommendation list top-to-bottom under the 7 Laws — routes each item to the right specialist (`superpowers:*`, `ralph`, `workspace-surface-audit`, `simplify`, `security-review`, `schedule`, `loop`), falls back to inline behavior when a specialist isn't installed, verifies per item, halts on `needs-approval` | @naimkatiman | |
There was a problem hiding this comment.
The phrasing "any agent's recommendation list" is slightly inconsistent with the original "any Claude recommendation list" (where "Claude" was used as an adjective) and deviates from the intended change described in the PR summary ("any agent recommendation list"). Using "agent" as an adjective here would be more consistent with the rest of the refactor and the original phrasing style.
Suggested change
| | **`proceed-with-the-recommendation`** ⭐ | Walks any agent's recommendation list top-to-bottom under the 7 Laws — routes each item to the right specialist (`superpowers:*`, `ralph`, `workspace-surface-audit`, `simplify`, `security-review`, `schedule`, `loop`), falls back to inline behavior when a specialist isn't installed, verifies per item, halts on `needs-approval` | @naimkatiman | | |
| | **`proceed-with-the-recommendation`** ⭐ | Walks any agent recommendation list top-to-bottom under the 7 Laws — routes each item to the right specialist (`superpowers:*`, `ralph`, `workspace-surface-audit`, `simplify`, `security-review`, `schedule`, `loop`), falls back to inline behavior when a specialist isn't installed, verifies per item, halts on `needs-approval` | @naimkatiman | |
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
1 participant
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
Follow-up to #38. Same low-risk Claude→agent phrasing-only refactor, applied across the next batch of skills:
gateguard×2 (forces Claude → forces the agent; Claude tends to guess → the agent tends to guess)token-budget-advisor×1 (before Claude answers → before the agent answers)verification-loop×2 (description + prose: Claude Code sessions → agent coding sessions)strategic-compact×1 (CLAUDE.md instructions→Agent instructions (from CLAUDE.md / AGENTS.md))skills/README.md×2 (Claude's recommendation list → the agent's recommendation list; any Claude recommendation list → any agent recommendation list)Files
skills/plugins/continuous-improvement/skills/(regenerated bynpm run buildper thebin/generate-plugin-manifests.mjspipeline; the sourceskills/README.mdsays these mirrors are auto-generated)10 files total, +15 / -15. Within the 15-file commit-size gate.
Out of scope (deliberately left alone)
proceed-with-the-recommendation— already covered by refactor(skill): make proceed-with-the-recommendation agent-agnostic #38workspace-surface-audit— most Claude references are legitimate product references (set up Claude Codetrigger phrase,Claude or Codex pluginsaudit list,AGENTS.md, CLAUDE.mdinstall-config path list). Deferred to a separate, more careful audit.ralph— both Claude references are legitimate (section header# Using Claude Code, file pathscripts/ralph/CLAUDE.md)token-budget-advisor.mdline 133 attribution to the upstream "Token Budget Advisor for Claude Code" project (proper noun, not generic phrasing)Test plan
npm test: 238/238 pass (build + tests)check-skill-mirror.test.mjspasses (source + mirror byte-identical after regen)