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/mitodl/agent-kit/witan-codenpx skills add mitodl/agent-kit --skill witan-codegit clone --depth 1 https://github.com/mitodl/agent-kitWhat 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 | $0.00120 | $0.01466 |
| Opus 5 | $0.00060 | $0.00733 |
| Sonnet 5 | $0.00024 | $0.00293 |
| Haiku 4.5 | $0.00012 | $0.00147 |
Grade A, and why
witan-code 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 yesterday.
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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Graph
A per-repo, tree-sitter-derived graph of symbols (functions, methods, classes,
modules) and their relationships (Calls, References, Imports,
Inherits), plus a cross-repo bridge linking services through shared
contracts (env vars, HTTP endpoints, packages, deployments). Indexing is
automatic — a SessionStart hook seeds/refreshes the whole repo in the
background, and a PostToolUse hook incrementally reindexes each file you
edit — so you rarely need to invoke the CLI yourself.
When to use this vs. grep / the Explore agent
Reach for code_* tools when the question is structural, not textual:
- "Where is
Service.rundefined?" →code_find_definition/code_search_symbol - "What calls this function, anywhere in the repo?" →
code_callers/code_find_references - "If I change this, what breaks?" (transitive blast radius) →
code_impact - "What symbols does this file define?" →
code_symbols_in_file - "Which other repo reads this env var / calls this endpoint / imports this package?" →
code_interface_consumers/code_interface_providers/code_cross_repo_impact
Grep is still the right tool for literal string/comment searches, one-off text
matches, or a repo with no code graph yet. The two are complementary: grep
finds text; code_* tools resolve symbols and their relationships,
which grep cannot do (it can't tell you a function's transitive callers or
which service consumes an endpoint another service serves).
Caveat: Calls/References/Imports/Inherits edges are heuristic
(syntactic name resolution, not a true call graph) — treat impact/caller
results as a high-recall starting point, not a verified answer. Defines and
Contains are exact.
On invocation
- No args → Check readiness, then show the tool reference below.
reindex→ call thecode_reindexMCP tool (orwitan-code reindexif running the CLI directly) to force a full rebuild of the current repo, ignoring content hashes. Use when the graph looks stale and you don't want to wait for the incremental hooks to catch up.
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.
- yesterday First seen · 117 lines · 120 tokens per session scan A 781041fd2123
witan-code is a skill published in the GitHub repository mitodl/agent-kit (2 stars, last pushed 3d ago), licensed BSD-3-Clause. It adds 120 tokens to every session and 1,466 once invoked, about $0.0006 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.
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…