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 tomzx/agents --skill find-documentation-gapsgit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/find-documentation-gaps)<a href="https://agentmods.dev/skills/tomzx/agents/find-documentation-gaps"><img src="https://agentmods.dev/badge/skills/tomzx/agents/find-documentation-gaps.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 129 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00036 | $0.02458 |
| Opus 5 | $0.00018 | $0.01229 |
| Sonnet 5 | $0.00007 | $0.00492 |
| Haiku 4.5 | $0.00004 | $0.00246 |
Grade A, and why
find-documentation-gaps 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 4d 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 — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TODAY=!date +%Y-%m-%d
Documentation Gaps
Identifies public-facing code — functions, classes, modules, CLI commands, REST endpoints, and config options — that is missing or has stale documentation. Ranks gaps by how visible and heavily-used the surface area is, so the most impactful docs get written first.
Prerequisites
- Working directory is the root of the repository
- Optional:
$1— path to limit the scan (defaults to.) - Optional language-specific tools:
- Python:
interrogate(uv tool install interrogate) for docstring coverage - JavaScript/TypeScript:
typedocorjsdoccomment detection via rg - Go:
golintor rg for unexported godoc
- Python:
What Counts as a Documentation Gap
| Surface | Missing if... |
|---|---|
| Public function / method | No docstring, no JSDoc/godoc comment |
| Public class / interface | No class-level docstring or comment |
| Module / package | No module docstring or __init__.py docstring |
| CLI command / subcommand | No help= / --help text, or help text is a placeholder |
| REST / RPC endpoint | No docstring, no OpenAPI annotation, no comment describing purpose, params, and response |
| Config key / env variable | Key present in config file or .env.example but not documented in README or reference doc |
| Exported type / constant | No accompanying comment explaining purpose and valid values |
Steps
1. Detect Language and Project Type
find ${1:-.} -type f | sed 's/.*\.//' | sort | uniq -c | sort -rn | head -10
ls README* docs/ CHANGELOG* openapi* swagger* 2>/dev/null
2. Measure Docstring / Comment Coverage
Python — interrogate:
interrogate ${1:-.} -v --ignore-init-method --ignore-magic --ignore-private 2>/dev/null | tail -30
Flag any module, class, or function with MISSING in the output.
Python — rg fallback:
# Find public functions/classes with no immediately following docstring
python3 -c "
import ast, sys, os
for root, dirs, files in os.walk('${1:-.}'):
dirs[:] = [d for d in dirs if not d.startswith('.') and d not in ('__pycache__', '.venv', 'node_modules')]
for f in files:
if not f.endswith('.py'): continue
path = os.path.join(root, f)
try:
tree = ast.parse(open(path).read())
except:
continue
for node in ast.walk(tree):
if isinstance(node, (ast.FunctionDef, ast.AsyncFunctionDef, ast.ClassDef)):
if node.name.startswith('_'): continue
if not (node.body and isinstance(node.body[0], ast.Expr) and isinstance(node.body[0].value, ast.Constant)):
print(f'{path}:{node.lineno} {type(node).__name__} {node.name}')
" 2>/dev/null | head -50
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.
- 4d ago First seen · 273 lines · 36 tokens per session scan A f4e2ecd4ec6d
find-documentation-gaps is a skill published in the GitHub repository tomzx/agents (6 stars, last pushed 4d ago), licensed MIT. It adds 36 tokens to every session and 2,458 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 2026-09-03.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…