claude-tap is a local proxy and trace viewer for AI coding agents, recording and displaying their API requests, prompts, tool calls, responses, context, and token usage. It helps developers inspect and compare agent runs from tools such as Claude Code, Codex CLI, Gemini CLI, Cursor CLI, and others, while the catalogue skills and instruction support work with the project.
Borrowing it
Nothing to install: this file belongs to liaohch3/claude-tap. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/liaohch3/claude-tap/main/.agents/skills/legibility-check/SKILL.mdgit clone --depth 1 https://github.com/liaohch3/claude-tapWrote 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/liaohch3/claude-tap/legibility-check)<a href="https://agentmods.dev/skills/liaohch3/claude-tap/legibility-check"><img src="https://agentmods.dev/badge/skills/liaohch3/claude-tap/legibility-check/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/liaohch3/claude-tap/legibility-check"><img src="https://agentmods.dev/badge/skills/liaohch3/claude-tap/legibility-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00068 | $0.00536 |
| Opus 5 | $0.00034 | $0.00268 |
| Sonnet 5 | $0.00014 | $0.00107 |
| Haiku 4.5 | $0.00007 | $0.00054 |
Grade A, and why
legibility-check 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 11d 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.
What it actually says
Legibility Check
Run deterministic checks for maintainer docs that mirror what CI enforces via .github/workflows/legibility.yml. Catching these locally saves a round-trip to CI.
What it checks
- Standards freshness — every
.agents/docs/standards/*.mdmust have frontmatter withowner,last_reviewed(ISO date), andsource_of_truth. Files reviewed more than 60 days ago produce a warning. - Architecture manifest — every path listed in
.agents/docs/architecture/manifest.yamlunderexpected_paths:must exist in the repo. - Plan state drift — every
.agents/docs/plans/**/*.mdmust have astatusfrontmatter field (active,completed, orcancelled). Completed plans must not contain unchecked- [ ]checkboxes (outside fenced code blocks).
Run
uv run python scripts/check_legibility.py
Options:
--freshness-days N— change the staleness threshold (default: 60)--strict-freshness— promote stale warnings to failures--repo-root PATH— override repo root (default: cwd)
Fixing common failures
| Failure | Fix |
|---|---|
missing frontmatter key 'X' |
Add the missing key to the YAML frontmatter block at the top of the file |
last_reviewed must be ISO date |
Use YYYY-MM-DD format |
last_reviewed ... is stale |
Update last_reviewed to today's date after reviewing the content |
expected path missing: X |
Either create the file or remove the stale entry from manifest.yaml |
status must be one of [...] |
Add status: active (or completed/cancelled) to plan frontmatter |
completed plan still contains unchecked TODO |
Check off remaining items or change status back to active |
After fixing
Re-run the check to confirm all issues are resolved before committing:
uv run python scripts/check_legibility.py && echo "All clear"
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.
- 11d ago First seen · 46 lines · 68 tokens per session scan A 8a3edb8394be
legibility-check is a skill published in the GitHub repository liaohch3/claude-tap (3,189 stars, last pushed 15d ago), licensed MIT. It adds 68 tokens to every session and 536 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
prompt-optimization
Improves LLM-facing context while preserving intent, execution boundaries, and proportional work. Use when creating or reviewing prompts, agent definitions, skill definitions, or other instructions for an LLM.
recipe-eval-prompt
Compares original and optimized prompts through repeated blind paired execution in git worktrees. Use when evaluating prompt improvement effects or learning prompt engineering through concrete examples.
knowledge-base
Retrieves and updates project-specific prompt knowledge from comparison evidence and user feedback. Use only for prompt analysis or post-comparison learning within a Rashomon evaluation.
interview-me
Deep-dive spec interviewer. Reads a file, GitHub issue, or requirement, analyzes it against the codebase, then conducts a rigorous 1-on-1 interview using AskUserQuestion to produce a comprehensive, opinionated specification document. Acts as a collaborative architect with active pushback. Also runs --verify to detect…
worktree-execution
Creates, pins, and cleans isolated Git worktree pairs for comparison trials. Use only when a Rashomon prompt or skill evaluation needs paired execution environments or orphan recovery.
recipe-eval-skill
Creates or updates Claude Code skills through interactive dialog, then evaluates effectiveness with sequential paired comparisons. Use when creating new skills, updating existing skills, or evaluating skill quality.