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 Filip-Podstavec/claude-leverage --skill repo-mapgit clone --depth 1 https://github.com/Filip-Podstavec/claude-leverageWrote 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/filip-podstavec/claude-leverage/repo-map)<a href="https://agentmods.dev/skills/filip-podstavec/claude-leverage/repo-map"><img src="https://agentmods.dev/badge/skills/filip-podstavec/claude-leverage/repo-map/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/filip-podstavec/claude-leverage/repo-map"><img src="https://agentmods.dev/badge/skills/filip-podstavec/claude-leverage/repo-map.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 Prompt Injection · line 7 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 35 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00070 | $0.01736 |
| Opus 5 | $0.00035 | $0.00868 |
| Sonnet 5 | $0.00014 | $0.00347 |
| Haiku 4.5 | $0.00007 | $0.00174 |
Grade A, and why
repo-map scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/repo-map
What it does
Maintains the architecture-overview mermaid block in README.md (or a
target file you pass). Idempotent: re-runs replace only the block between
the markers; surrounding README content is untouched.
The block:
<!-- repo-map:start -->
<!-- This block is regenerated by skills/repo-map. Do not hand-edit. -->
<!-- Re-run /repo-map to refresh after directory structure changes. -->
```mermaid
flowchart TB
...
## Workflow
1. **Resolve target file.** Default `README.md` in the repo root. If
`$ARGUMENTS` includes a path, use that.
2. **Resolve repo root.** Walk up from cwd looking for `.git/`. If not in
a git repo, STOP and report.
3. **Walk the repo.**
- Top-level: read every directory entry; skip dotfiles unless `.codex`
or `.claude*` (those are tooling).
- For each top-level dir, list its immediate children (2 levels total).
- For each dir, check for an `AGENTS.md` and read its first heading +
description (first paragraph). That becomes the node label tooltip.
- Skip ignored paths: anything under `bench/archive-token-savings-thesis/`,
`node_modules`, `__pycache__`, `.git`, `dist`, `build`, `.next`,
`.pytest_cache`, `target`, `vendor`.
4. **Categorize** the top-level dirs into mermaid subgraphs:
- `Agents & skills` — `agents/`, `skills/`, `commands/`, `.codex/agents/`
- `Hooks & scripts` — `hooks/`, `scripts/`, `scripts/hooks/`
- `Docs & tests` — `docs/`, `tests/`, `templates/`, `workflows/`, `*-docs/`
- `Config` — `.claude-plugin/`, `.codex/`, `.github/`
- `Archive` — `bench/` (shown collapsed)
- `Other` — everything else, alphabetical
5. **Emit a flowchart** with one node per non-trivial directory. Edges go
from a "Host (Claude Code / Codex)" node to the appropriate Agents &
skills subgraph, and from Hooks to scripts/hooks/. Keep the diagram
small (≤30 nodes). If the repo has many top-level dirs, group
aggressively.
6. **Validate with mmdc if available.** Run
`mmdc -i <tmp.mmd> -o <tmp.svg>` against the generated mermaid. If it
errors, read the error, fix the mermaid syntax (common offenders:
special characters in labels — wrap in quotes; reserved IDs like
`end`/`class` — pick a different ID; inconsistent arrow syntax), and
retry up to 3 times. If `mmdc` is not on PATH, skip validation with a
one-line warning.
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.
- 10d ago First seen · 164 lines · 70 tokens per session scan A 3fe15fbf9391
repo-map is a skill published in the GitHub repository Filip-Podstavec/claude-leverage (68 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 1,736 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
OCR Review-to-Approval Loop
Drive a PR to an approved code review by looping OCR's multi-agent review and address steps. Runs /ocr:review then /ocr:address repeatedly until the review verdict is APPROVE, then one final /ocr:address for leftover suggestions, posting every review and every address round to the GitHub PR as comments. Use when the…
codex-changelog
This skill should be used when the user asks to check for new Codex CLI (codex-cli) releases, "what changed in Codex", "any Codex updates", "check codex releases", "diff the codex version", or wants Codex CLI releases reviewed for changes relevant to THIS repo's Codex bridge. Reads a locally-stored last-checked…
git-workflow
Enforces the release-branch Git model: scaffold feature branches, open PRs with review checks, cut releases with tags, and view workflow reference.
changelog-generator
Generates a structured CHANGELOG.md following Keep a Changelog format from git history and ABD handoff artifacts. Prepends new version sections to existing changelogs.
pre-commit
Fast pre-commit quality gate: scans staged files for secrets, dead code, naming issues, merge conflict markers, and direct-to-main commits. Installs as a git hook via /pre-commit install.
changelog-generator
Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.