docs(sable-5u7): fix llms.txt typo + correct platform skill counts (B8)#131
Merged
Conversation
Two corrections found while cross-reading our llms.txt against docs.rafter.so/llms.txt and verifying against the current AGENT_SKILLS source: 1. Line 16 had a truncated sentence — '(ode is immediately after analysis)'. Replaced with '(code is deleted immediately after analysis)' matching the wording at line 139 of the same file. 2. The Supported Agent Platforms table understated the skill count for Claude Code and Codex CLI. Both platforms install 3 security skills today (rafter, rafter-secure-design, rafter-code-review per node/src/commands/agent/init.ts:27 AGENT_SKILLS), not 2. OpenClaw installs the ClawHub-shaped rafter-security skill (single SKILL.md in workspace/skills/rafter-security/). The docs.rafter.so/llms.txt is intentionally different — covers the docs site, not the package — but the factual claims (platform names, install flag, what install does) should agree. This commit aligns the factual claims. Cross-rig coordination on the secbolt llms.txt is being nudged separately to juno. Closes sable-5u7.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Two corrections found while cross-reading our `llms.txt` against `docs.rafter.so/llms.txt` and verifying against the current `AGENT_SKILLS` source.
Typo fix
Line 16 had a truncated sentence:
Looks like a partial edit artifact — the line at L139 in the same file uses the correct phrasing:
Aligned L16 to that wording.
Skill-count fix
The "Supported Agent Platforms" table understated skill counts:
Verified against `node/src/commands/agent/init.ts:27 AGENT_SKILLS`, which lists three: `rafter`, `rafter-secure-design`, `rafter-code-review`. The fourth skill (`rafter-skill-review`, tightened in PR #126) is NOT in `AGENT_SKILLS` and so doesn't ship to platforms — separate question whether it should (filing as follow-up).
OpenClaw uses a different shape — the canonical ClawHub install at `~/.openclaw/workspace/skills/rafter-security/SKILL.md` (single SKILL.md, not the multi-skill tree).
Out of scope
Target: `maylist`.
Closes sable-5u7.
🤖 Generated with Claude Code
Co-Authored-By: Claude Opus 4.7 noreply@anthropic.com