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/ssbun/csl-agent-kit/project-indexnpx skills add SSBun/csl-agent-kit --skill project-indexgit clone --depth 1 https://github.com/SSBun/csl-agent-kitWrote 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/ssbun/csl-agent-kit/project-index)<a href="https://agentmods.dev/skills/ssbun/csl-agent-kit/project-index"><img src="https://agentmods.dev/badge/skills/ssbun/csl-agent-kit/project-index.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 | $0.00064 | $0.00689 |
| Opus 5 | $0.00032 | $0.00345 |
| Sonnet 5 | $0.00013 | $0.00138 |
| Haiku 4.5 | $0.00006 | $0.00069 |
Grade A, and why
project-index 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 5d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Index
Choose likely repositories from an incomplete local business index before reading code. No match does not prove absence.
CLI and Data
Resolve this skill directory and run its scripts/project-index.js with:
list
get <project-id>
query <term>...
upsert <project-id> # complete record JSON on stdin
validate
Commands emit JSON. Data lives at $CSL_AGENT_KIT_HOME/project-indexes/index.json (default ~/.csl-agent-kit/project-indexes/index.json); snapshots use adjacent snapshots/.
One projects entry is one independent Git repository; a repository container is not a project. Records contain name, absolute root, owns, doesNotOwn, terms, useWhen, and optional pages; glossary owns terms, aliases, distinctions, and evidence. Human-confirmed responsibilities are authority; CodeGraph stays generated per repository.
Never scan unindexed repositories, bulk-create placeholders, generate screenshots, or add vector search.
Route a Task
- Derive two to six concise business terms; pass each meaningful phrase as one argument to
query. - The script returns at most eight candidates with coverage, matches, conflicts, pages, and snapshot status. Rerank at most three from their records and request intent.
- Report coverage, reasons,
doesNotOwnconflicts, and pages. With no result, state that only listed projects were searched and offer to add one; do not search other code. - When page identity matters, load
snapshotPathwith the host image reader, or provide the absolute path when inline display is unavailable. Ask the user to confirm ambiguity. - Only after repository confirmation, narrow lookup inside it.
Verify Code Ownership
- Check
command -v codegraph, thencodegraph status <project-root> --json. - If unavailable or stale, mark ownership unverified. Ask before
codegraph init <project-root>orcodegraph sync <project-root>because they write generated data. - Use
codegraph query <search> -p <project-root> -l 10 -j; usecallersorcalleesonly for a returned symbol needing relationship evidence. - Confirm important conclusions against a source entry point, route, registration, or call relationship. Without such evidence, report only the business candidate.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 50 lines · 64 tokens per session scan A 961d8a81ac72
project-index is a skill published in the GitHub repository SSBun/csl-agent-kit (10 stars, last pushed 4d ago), licensed MIT. It adds 64 tokens to every session and 689 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…