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 agentmods add skills/yujiachen-y/codebase-recon-skill/codebase-reconnpx skills add yujiachen-y/codebase-recon-skill --skill codebase-recongit clone --depth 1 https://github.com/yujiachen-y/codebase-recon-skillWrote 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/yujiachen-y/codebase-recon-skill/codebase-recon)<a href="https://agentmods.dev/skills/yujiachen-y/codebase-recon-skill/codebase-recon"><img src="https://agentmods.dev/badge/skills/yujiachen-y/codebase-recon-skill/codebase-recon.svg" alt="Measured on agentmods" 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 | $0.00047 | $0.01531 |
| Opus 5 | $0.00023 | $0.00766 |
| Sonnet 5 | $0.00009 | $0.00306 |
| Haiku 4.5 | $0.00005 | $0.00153 |
Grade A, and why
codebase-recon scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Recon
Analyze git history to understand a codebase before reading any code. Reveals project health, risk areas, team structure, and development momentum.
Inspired by "The Git Commands I Run Before Reading Any Code" by Ally Piechowski.
Phase 1: Probe
Before running analysis, determine repo scale to calibrate time windows and result counts.
Run this single shell command to collect repo vitals:
echo "COMMITS=$(git rev-list --count HEAD)" && \
echo "FIRST_COMMIT=$(git log --reverse --format='%ad' --date=short | head -1)" && \
echo "LATEST_COMMIT=$(git log --format='%ad' --date=short | head -1)" && \
echo "BRANCHES=$(git branch -a | wc -l | tr -d ' ')"
Use the commit count to set parameters for Phase 2:
| Repo Size | Commits | WINDOW (--since) |
N (--head) |
|---|---|---|---|
| Small | <500 | (omit --since) | 10 |
| Medium | 500-10k | 1 year ago |
20 |
| Large | >10k | 6 months ago |
30 |
Print the Repo Vitals line immediately:
Repo Vitals: Age: [FIRST_COMMIT to LATEST_COMMIT] | Commits: [COMMITS] | Branches: [BRANCHES] | Analysis window: [WINDOW or "all time"]
Phase 2: Parallel Analysis
Run all 7 commands in parallel (they are independent). Substitute WINDOW and N from Phase 1. For small repos, omit --since flags entirely.
2a. Code Hotspots
Most-changed files in the analysis window:
git log --format=format: --name-only --since="WINDOW" | sort | uniq -c | sort -nr | head -N
2b. Bus Factor
All-time contributor ranking by commit count:
git shortlog -sn --no-merges
2c. Bug Magnets
Files most associated with bug-fix commits:
git log -i -E --grep="fix|bug|broken" --name-only --format='' --since="WINDOW" | sort | uniq -c | sort -nr | head -N
2d. Team Momentum
Commit frequency by month (all time):
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.
- 3d ago First seen · 171 lines · 47 tokens per session scan A c39280cd2948
codebase-recon is a skill published in the GitHub repository yujiachen-y/codebase-recon-skill (36 stars, last pushed 4mo ago), licensed MIT. It adds 47 tokens to every session and 1,531 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…