Borrowing it
Nothing to install: this file belongs to aspenkit/aspens. 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/aspenkit/aspens/main/.agents/skills/repo-scanning/SKILL.mdgit clone --depth 1 https://github.com/aspenkit/aspensWrote 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/aspenkit/aspens/repo-scanning)<a href="https://agentmods.dev/skills/aspenkit/aspens/repo-scanning"><img src="https://agentmods.dev/badge/skills/aspenkit/aspens/repo-scanning/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/aspenkit/aspens/repo-scanning"><img src="https://agentmods.dev/badge/skills/aspenkit/aspens/repo-scanning.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 | $0.00027 | $0.01300 |
| Opus 5 | $0.00014 | $0.00650 |
| Sonnet 5 | $0.00005 | $0.00260 |
| Haiku 4.5 | $0.00003 | $0.00130 |
Grade A, and why
repo-scanning 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 9d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are working on aspens' repo scanning system — a fully deterministic analyzer (no LLM calls) that detects languages, frameworks, structure, domains, entry points, size, and health issues for any repository.
Domain purpose
Scanning is the foundation every other command builds on. scanRepo() must produce stable, reproducible results from any repo on disk — even a freshly-cloned one with no manifests parsed yet — so doc init, doc sync, doc impact, and doc graph can decide what to generate, which target (Claude / Codex) is appropriate, and which domains warrant skills. Determinism is the contract: the same repo at the same commit must always produce the same scan.
Key Concepts
- scanRepo() return shape:
{ path, name, languages[], frameworks[], structure, domains[], entryPoints[], hasClaudeConfig, hasClaudeMd, hasCodexConfig, hasAgentsMd, repoType, size, health }— order matters:repoTypeandhealthdepend on prior fields - Multi-target detection: Scanner checks for both
.claudedir +AGENTS.md(Claude Code) and.codexdir +AGENTS.md(Codex CLI) to inform target selection duringdoc init - Detection via marker files: Languages detected by presence of files like
package.json,go.mod,Cargo.toml— not by scanning source extensions - Framework detection: JS/TS from
package.jsondeps, Python fromrequirements.txt/pyproject.toml/Pipfile, Go fromgo.modcontents, Ruby fromGemfile - Domain detection: Scans dirs under source root + repo root, skips
SKIP_DIR_NAMESset (structural/build/IDE/.NET/Java/Rust build dirs), requires at least one source file viacollectModules() - extraDomains: User-specified domains merged via
mergeExtraDomains()— marked withuserSpecified: true, resolved against source root then repo root - Source root: First match of
src,app,lib,server,pagesviafindSourceRoot(); for nested-project layouts (e.g.~/apps/MyApp/MyApp/MyApp.csproj), if repo root has exactly one non-skip child with a project manifest, that child is promoted as the source root and excluded from domain scanning at repo root to avoid double-counting - Size estimation: Lines estimated at ~40 bytes/line from
stat.size, walk capped at depth 5, skipsbin/obj/targetbuild output alongsidenode_modules/dist/etc. - Graph is opt-out:
scanCommandbuilds graph by default (options.graph !== false); errors are caught and only logged with--verbose - Health checks are language-aware:
.gitignorechecks for missingnode_modules/,__pycache__/,target/, virtualenv dirs, and uncommitted.envfiles are gated on detected languages
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.
- 9d ago First seen · 56 lines · 27 tokens per session scan A fd9328df9106
repo-scanning is a skill published in the GitHub repository aspenkit/aspens (99 stars, last pushed 24d ago), licensed MIT. It adds 27 tokens to every session and 1,300 once invoked, about $0.0001 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
debug
Systematic 4-phase debugging with escalation protocol. Use when saying "debug", "investigate bug", "find root cause", "why is this failing", or "fix this bug".
docverity
Check whether a project's documentation still matches its code, and report stale or wrong claims with suggested fixes. Use this after editing, renaming, moving, or deleting source files, CLI flags, environment variables, or functions, to catch docs you may have just made inaccurate; when the user asks whether the…
printing-press-polish
Polish a generated CLI to pass verification and become publish-ready. Runs diagnostics (dogfood, verify, scorecard, go vet, gosec), automatically fixes all issues (verify failures, static-analysis findings, dead code, descriptions, README, MCP tool quality), reports the before/after delta, and offers to publish. Use…
printing-press-amend
Amend a published CLI from one of two input sources: (1) dogfood mode mines the active Claude Code session transcript for friction (missing flags, hand- rolled API payloads, silent-null returns); (2) direct-input mode accepts user-supplied asks (rename a command, add commands or feeds, fix a named bug, optionally…
printing-press-output-review
Internal sub-skill: agentic review of a printed CLI's sampled command output for plausibility issues that rule-based checks can't encode (substring-match relevance, format bugs, silent source drops, ranking failures). Invoked via the Skill tool by the main printing-press skill at Phase 4.85 and printing-press-polish…
fix
Dispatch fix subagent for FIX-FIRST gaps from review, re-review, then diagnose unresolved failures after 2 loops.