Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add RockyHong/super-bootstrap --skill check-docs-consistencygit clone --depth 1 https://github.com/RockyHong/super-bootstrapWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/rockyhong/super-bootstrap/check-docs-consistency)<a href="https://agentmods.dev/skills/rockyhong/super-bootstrap/check-docs-consistency"><img src="https://agentmods.dev/badge/skills/rockyhong/super-bootstrap/check-docs-consistency.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00034 | $0.03024 |
| Opus 5 | $0.00017 | $0.01512 |
| Sonnet 5 | $0.00007 | $0.00605 |
| Haiku 4.5 | $0.00003 | $0.00302 |
Grade A, and why
check-docs-consistency scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Check Docs Consistency
Stateless scan. Read docs, cross-reference, write timestamped report. Report-only — resolution is the user's call.
When to Use
User invokes /super-bootstrap:check-docs-consistency when:
- Starting a new feature pipeline (verify source of truth before writing specs)
- Drift pain surfaces ("wait, didn't we decide the opposite?")
- After a batch of merges that touched multiple docs
- Periodically as a health check (weekly or per-milestone)
Doc Surface
The scan reads **/*.md at any depth and keeps the authored project docs. The filter drops generated and vendored Markdown — paths under node_modules/, vendor/, .git/, dist/, build/, target/, .venv/, and the scan's own .review/ reports. The kept set is the doc surface, wherever the project holds it: a docs/ tree, a root README plus scattered *.md, documentation/, .github/, or any mix.
The glob already includes the orchestration files (CLAUDE.md, .claude/agents/*.md, .claude/skills/**/SKILL.md); Step 1 mines those specifically for path references and ownership statements.
Extend the exclusion list per project when a tree carries *.md that is generated or vendored output rather than authored project doc (e.g. .next/, coverage/, __pycache__/).
Procedure
Step 0: Pre-flight — Block If a Prior Report Is Unprocessed
Glob .review/docs-consistency-*.md. (Step 0 reads .review/ to find prior reports; Step 1's doc-surface scan excludes that same dir — see Doc Surface.)
If a report from a previous date exists, stop and surface the path(s): findings route through the user's triage first (fix / dismiss / track per project convention), and the processed report is deleted or archived before the next scan of the same type. Re-invoke after.
The skill produces no second report while a prior one is pending. Same-day re-runs are exempt (they overwrite today's file; see Step 3). The user may explicitly override the block to force a fresh scan.
Step 1: Discover and Read All Docs (one pass)
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 206 lines · 34 tokens per session scan A 6ba476e545b5
check-docs-consistency is a skill published in the GitHub repository RockyHong/super-bootstrap (3 stars, last pushed 3d ago), licensed MIT. It adds 34 tokens to every session and 3,024 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
memory-graveyard
Audit which entries in your project's MEMORY.md Claude actually reads. Use when the user wants to find dead memory entries, broken pointers in MEMORY.md, orphan memory files, or surface entries that fall below the system-prompt truncation cutoff. Triggers on "audit MEMORY.md", "dead memory entries", "broken memory…
skill-graveyard
Audit which Claude Code skills you actually invoke. Use when the user wants to find dead/unused skills, hallucinated skill invocations, per-project skill stats, or token cost of installed skill metadata. Triggers on "what skills don't I use?", "clean up my skills", "why didn't this skill work?", "audit skills". Runs…
mcp-graveyard
Audit which MCP server tools your Claude Code sessions actually invoke. Use when the user wants to find dead MCP servers (configured but never called), hallucinated MCP tool calls, or per-project MCP usage. Triggers on "which MCP servers don't I use?", "clean up MCP config", "remove unused MCP servers", "audit MCP…
image-upload
Grab an image from the clipboard and analyze it. Use when the user says image upload, paste, screenshot, clipboard, or asks to look at something they copied.
ln-22-codebase-auditor
Audits cross-cutting code health, security, delivery, and maintainability when no specialist audit is primary. Not for a single delivery review.
ln-51-opportunity-evaluator
Evaluates new product opportunities using demand, channels, competition, and economics. Not for committed-backlog or implementation planning.