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/getklai/klai/codeindex-clinpx skills add GetKlai/klai --skill codeindex-cligit clone --depth 1 https://github.com/GetKlai/klaiWhat 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 | $0.00077 | $0.01009 |
| Opus 5 | $0.00039 | $0.00504 |
| Sonnet 5 | $0.00015 | $0.00202 |
| Haiku 4.5 | $0.00008 | $0.00101 |
Grade A, and why
codeindex-cli 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 2d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CodeIndex CLI Commands
Use these commands only for explicit index/setup/maintenance requests. For normal agent work, use the MCP tools (query, context, impact) and verify stale results against source files.
Commands
analyze — Build or refresh the index
codeindex analyze
Run from the project root. This parses all source files, builds the knowledge graph, writes it to ~/.codeindex/<ProjectName>/ (global cache — NEVER inside the working copy), and generates CLAUDE.md / AGENTS.md context files in the project root.
| Flag | Effect |
|---|---|
--force |
Force full re-index even if up to date |
--embeddings |
Enable embedding generation for semantic search (off by default) |
When to run: First time in a project or when the user explicitly asks to
rebuild the index. Do not run this automatically just because
codeindex://repo/{name}/context reports stale data.
For Klai in Conductor, do not run ad hoc analyze/update commands from a
feature worktree. That warning can be caused by a worktree overlay or by the
registered checkout not being on main. Run scripts/codeindex-health.sh first;
only if it reports the shared base index is stale, run
scripts/codeindex-health.sh --repair.
update — Refresh an existing index
codeindex update
Use this only when the user explicitly asks to refresh a stale index. For Klai
Conductor worktrees, prefer scripts/codeindex-health.sh --repair for the
shared main index.
status — Check index freshness
codeindex status
Shows whether the current repo has a CodeIndex index, when it was last updated, and symbol/relationship counts. Use this to check if re-indexing is needed.
clean — Delete the index
codeindex clean
Deletes the repo's entry under ~/.codeindex/<ProjectName>/ and unregisters it from the global registry. Use before re-indexing if the index is corrupt or after removing CodeIndex from a project. Never deletes anything inside the working copy.
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.
- 2d ago First seen · 103 lines · 77 tokens per session scan A 0244ef60ff42
codeindex-cli is a skill published in the GitHub repository GetKlai/klai (11 stars, last pushed 2d ago), licensed MIT. It adds 77 tokens to every session and 1,009 once invoked, about $0.0004 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…