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 ckorhonen/swe-skills --skill repo-introspectiongit clone --depth 1 https://github.com/ckorhonen/swe-skillsWrote 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/ckorhonen/swe-skills/repo-introspection)<a href="https://agentmods.dev/skills/ckorhonen/swe-skills/repo-introspection"><img src="https://agentmods.dev/badge/skills/ckorhonen/swe-skills/repo-introspection/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/ckorhonen/swe-skills/repo-introspection"><img src="https://agentmods.dev/badge/skills/ckorhonen/swe-skills/repo-introspection.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00106 | $0.01220 |
| Opus 5 | $0.00053 | $0.00610 |
| Sonnet 5 | $0.00021 | $0.00244 |
| Haiku 4.5 | $0.00011 | $0.00122 |
Grade A, and why
swe:repo-introspection 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 12d 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SWE Repo Introspection
What This Skill Does
Use this skill to help an engineer or agent become productive in an unfamiliar codebase without guessing.
The report should explain:
- How the repository is organized
- How it is likely operated
- Where the important boundaries are
- Which surfaces look safest to touch next
When To Use
Use this skill when the user wants to:
- Understand an unfamiliar repository before editing it
- Prepare for delegation or planning
- Map tooling, entry points, and boundaries
- Find safe starting surfaces for follow-on work
Do Not Use
Do not use this skill for:
- Implementing a known change request
- Debugging one specific defect
- Writing a broad architecture vision that goes beyond visible repo evidence
Inputs To Confirm
Confirm or infer:
- Repo or package scope
- Whether the user wants a whole-repo view or only selected directories
- Whether recent activity or ownership context matters
What To Optimize For
- Concrete evidence from the repository
- Fast orientation
- Clear mental model of the codebase
- Accurate identification of entry points and working surfaces
- Explicit unknowns instead of speculation
Instructions
Step 1: Inspect The Root And Primary Docs
Start with the repo root, major directories, and the main documentation files.
Step 2: Identify Tooling And Runtime Shape
Find the main languages, frameworks, package managers, and build or runtime tooling.
Step 3: Locate Entry Points And Boundaries
Find likely entry points such as:
- App starts
- Services
- CLI commands
- Routes
- Workers
- Jobs
- Library exports
Map the major code surfaces and their responsibilities.
Step 4: Capture Validation And Automation Surfaces
Identify:
- Test locations
- Validation commands
- CI or automation surfaces
- Generated or machine-managed areas
Step 5: Note Active And Safe Areas
Inspect recent commits when useful to understand active areas or likely ownership.
Then summarize the safest and most relevant surfaces for follow-on work.
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.
- 12d ago First seen · 212 lines · 106 tokens per session scan A d6d605613acd
swe:repo-introspection is a skill published in the GitHub repository ckorhonen/swe-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 106 tokens to every session and 1,220 once invoked, about $0.0005 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
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
design-sync-upload
An uploader for design-system files such as DESIGN.md, tokens, logos, fonts, and images into Claude Design. It can either use an authenticated connection or prepare a folder and guide for manual upload.