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/chucklever/cel-kdev/semcodenpx skills add chucklever/cel-kdev --skill semcodegit clone --depth 1 https://github.com/chucklever/cel-kdevWhat 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 | $0.00153 | $0.04006 |
| Opus 5 | $0.00077 | $0.02003 |
| Sonnet 5 | $0.00031 | $0.00801 |
| Haiku 4.5 | $0.00015 | $0.00401 |
Grade A, and why
semcode scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 331 lines — stays where its author put it; the contents beside it link to each section on GitHub.
semcode
semcode is a local semantic index over source trees and lore.kernel.org archives. Its MCP tool descriptions document parameters well but say nothing about how the index goes stale, what the archive actually contains, or which query shapes are dangerous. Those are what generate false starts, and they are what this skill covers.
Before the first query
Five gates. Gates 1, 3, and 4 run before you send the query; gates 2 and 5 run before you use what came back. Each names the section that explains it; run them, do not just read them.
- Code lookup via MCP, and HEAD has moved since
semcode-mcpstarted? Any commit or rebase moves it, and on an stg branch so does everyrefresh,goto,push, orpop. Reindex the changed files first:semcode-index --git <range>..HEAD-- on an stg branch the range start is$(stg id {base}), on a plain branch the upstream ref. If you cannot tell whether HEAD moved, run it; it is cheap and idempotent. The CLI's worktree overlay is not a substitute: it reflects uncommitted edits only, not committed-but-unindexed blobs. -- Index freshness - About to trust a returned body? Grep the reported
path:startin the worktree, or look for a symbol the patch under review introduced. A hit proves the symbol was indexed at some point, not that it is in your tree. -- Index freshness - Searching lore? Run
ls $SEMCODE_DB/lore/and read what it prints. That output is the only source for the archive roster; quote it, not a list remembered from elsewhere. -- Lore: coverage - Expanding a thread? By message-id. From a search, only with a small
limit: the cost is a fixed per-message amount summed across every matched thread, and nothing shows you that number before you commit. -- Searching is cheap - Asserting absence or completeness, or did a lore or commit search feed
the conclusion? Emit the scope line in the template's shape. A verified
positive
find_functionhit does not need it. -- Say what you searched
What ships with it
2 files 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.
- yesterday First seen · 331 lines · 153 tokens per session scan A 8590c5472ed1
semcode is a skill published in the GitHub repository chucklever/cel-kdev (2 stars, last pushed 4d ago), licensed MIT. It adds 153 tokens to every session and 4,006 once invoked, about $0.0008 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…