codometer-triage — Claude Code skill: what it does, how to install
codometer-triage handles a failing codometer --check run: tells a limit breach apart from a stale report or a run that could not finish, and points at what to fix.
MIT 363 installs updated 2026-10-24
npx skills add organizzolini/codebase --skill codometer-triage -a claude-codeWhat codometer-triage does
The skill takes over when codometer --check exits non-zero. Most of its work is telling apart the three findings a run can produce: a breach, a committed report that no longer matches, and a run that never completed. Each gets its own repair.
Severity decides whether anything actually fails. warn reports the breach but keeps the exit code as it was; fail returns 1, and only if the run asked --check limits for a gate. A comment budget arrives as an ordinary limits[] entry against a custom.<label> metric, except instances name a file and a line for every block that went over. Trust the count carefully: the line scanner used for shell, TOML, SQL and HCL reads a comment marker inside a string literal as a real comment. Input declaration and flag details live in the sibling skills codometer-configure and codometer-measure.
Editing the limit's value to get a green check is the wrong repair, because the promise that limit records disappears along with the evidence. Compressed sizes also shift between Node releases, so a report written on one version can read stale on another with zero changes to the source. Pairing --output-json or --output-markdown with --check reports is refused outright.
What it helps with
- Read why
codometer --checkreturned a non-zero exit code - Shrink a comment block that blew its word or line budget
- Refresh a committed report instead of editing the limit
- Find a limit pointing at a metric the run never measured
- Fix a configuration rejected at load time
Example prompts for the agent
codometer --checkfailed on the bundle size limit — walk me through what to cut in the code, not the config.- The committed report reads stale even though nothing changed. Check which Node version it was written on.
- Three entries landed in
failures; sort them by cause and propose a fix for each.
How to install codometer-triage
1Skills CLI (Vercel)
npx skills add organizzolini/codebase --skill codometer-triage -a claude-code2Manually: put the files in place
~/.claude/skills/codometer-triage/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/codometer-triage/
1Skills CLI (Vercel)
npx skills add organizzolini/codebase --skill codometer-triage -a codex2Manually: put the files in place
.agents/skills/codometer-triage/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add organizzolini/codebase --skill codometer-triage -a cursor2Manually: put the files in place
.cursor/skills/codometer-triage/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install organizzolini/codebase projects/ic-suite/codometer/codometer-agents/skills/codometer-triage2Manually: put the files in place
.github/skills/codometer-triage/SKILL.md1Skills CLI (Vercel)
npx skills add organizzolini/codebase --skill codometer-triage -a gemini-cli2Platform CLI
gemini skills install https://github.com/organizzolini/codebase --path projects/ic-suite/codometer/codometer-agents/skills/codometer-triageManually: put the files in place
.devin/skills/codometer-triage/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add organizzolini/codebase --skill codometer-triage -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about codometer-triage
How do I install codometer-triage in Claude Code?
Run npx skills add organizzolini/codebase --skill codometer-triage -a claude-code. The skill file lands at ~/.claude/skills/codometer-triage/SKILL.md.
What does codometer-triage do?
It guides the agent through a codometer --check report and picks a repair per finding type: a breach, a stale report, or a run that failed. Comment budgets and rejected configurations get their own sections.
Is a stale report the same thing as a breach?
No. A breach means a metric crossed a limit declared for it. Staleness means the committed report disagrees with a fresh measurement, with or without any limit involved. One run can report both.
Source text
SKILL.md · MIT
--- name: codometer-triage description: Act on a codometer limit breach, a comment budget breach, a stale committed report, or a run that failed outright. Use when a codometer --check exits non-zero, when a size or count limit was breached, when a comment block ran past its word, line, or character budget, when a committed report reads stale against a fresh measurement even though nothing changed, when a limit fails to bind or an input matches no files, or before reaching for a repository's limit value to make a failing check pass. license: MIT --- # Acting on a codometer failure A `--check` run reports three different kinds of finding, and they call for three different responses. Reading which one occurred, rather than reacting to "the check failed," is most of this skill. ## A breach A metric went past a limit declared for it. The report names the metric, the limit's value, and its severity: - **`warn`** prints the breach and leaves the exit code alone. Nothing about the run fails; it is advance notice that a number is moving in a direction worth watching. - **`fail`** exits `1`, and only when the run asked `--check limits` for a gate at all — a `codometer measure --config <path>` measuring the same breach reports nothing wrong, because nothing asked it to gate. **The instinctive fix — raising the limit's `value` — is not an option.** The limit exists to keep a promise about the codebase's shape; loosening it on the same change that broke the promise erases the evidence the check existed to produce, and the next breach starts from a codebase that is already worse. Reduce what is actually being measured instead: - A size breach: shrink the input's own output — trim a dependency, split a bundle, delete dead code — rather than the number that reports it. The `codometer-configure` skill covers declaring an input and pointing it at compiled output correctly, which is a common reason a size looks larger than the code that produced it: an input measuring more than it should. - A convention-count breach (too many of something, or too few): the count is usually accurate — the fix is in the code the counter is watching, not in the counter's `value`. - A **comment budget** breach is a custom statistic like any other, gated by an ordinary `limits[]` entry against its `custom.<label>` metric — but its `instances` name a file and a line for each breaching block rather than only a total, because the thing measured is one block rather than a repository-wide count. Condense that block, or move the detail into documentation that has room for it. Check which reader measured it before trusting the count — shell, TOML, SQL, and HCL use a line scanner that reads a comment marker inside a string literal as a comment, and Python's comments go unmeasured entirely when the interpreter cannot be run. The `codometer-configure` skill has both caveats in full. - **A comment budget a language is not covered by is not a breach at all** — it is simply not measured. If a repository added a language codometer can parse comments in but nobody added a `comment` selector for it, that language's blocks run with no budget until one is declared; this is never something to diagnose as a false negative in the tool. If the limit's number was simply wrong for what this metric should hold going forward — not because of this change, but as a standing decision — that is a deliberate edit to make and explain on its own, never a side effect of getting one check to pass. ## Staleness `--check reports` compares a committed report against a fresh measurement and fails when they disagree, whether or not any limit is involved. Two causes produce this, and only one of them is a real regression: - **The code actually changed** and the committed report was never re-measured. Re-run with `--output-json`/`--output-markdown` to refresh it. - **The runtime changed.** Compressed sizes are Node-version dependent — the bundled zlib differs release to release — so a report written on one Node version and checked on another reads as stale with zero code changes involved. Check on the exact runtime the repository pins for everything else before concluding the source moved. A **breach** and **staleness** are reported as separate findings even when they come from the same run; do not read one as a symptom of the other. ## A run that failed outright Distinct from both of the above: the run itself could not finish, collected into `failures` in the report rather than folded into any metric. - **A limit bound to nothing.** The metric path names no measurement the run actually took — misspelled, or naming an analysis its input never ran, or genuinely ambiguous between two inputs. Fix the path in the configuration; the `codometer-configure` skill covers how a metric path resolves and why an ambiguous one is refused rather than guessed. - **An input matched no files while carrying a limit.** Declaring a limit against an input asserts its files exist, so an empty match means the glob stopped matching or the build that should have produced those files never ran — check the build step before touching the configuration. An input nobody limited that matches nothing is unremarkable and reports no failure. - **The configuration itself was rejected before anything measured.** A missing `format`, two `outputs` entries of the same type, a custom statistic naming none of `patterns`/`symbols`/`comment`, or an `outputs` entry selecting a `custom` label the top-level `custom` array never declared each fail the run at load time with the reason named. A configuration exporting a function instead of a plain object is a quieter version of the same problem: there is no config-as-function escape hatch any more, so it is not recognized and falls back to an empty configuration — which then fails on the missing `format` rather than on anything naming the real cause. Fix the configuration rather than the command line. A run with no `--config` at all is refused before anything is measured: pass `--config <path>` naming the configuration file. Every failure in one run is collected and reported together, so treat a report naming three as three things to fix, not one flaky run to retry. ## Before reaching for `--output-json`/`--output-markdown` Remember that the two `--output-*` flags and `--check` are independent, with no inferred relationship between them — the `codometer-measure` skill has the full flag table. Combining an `--output-*` flag with `--check reports` is refused outright: nothing can be stale in a report the same run just wrote, so that combination is a configuration mistake to fix, not a way to force a report current. `--inputs [globs...]` is independent of `--check` too — narrowing a `measure` run to exactly the given globs does not change whether it gates or writes. There is no `--directory` on `measure`: a run always measures the process's own working directory. The `configuration` subcommand is the one place `-d, --directory` still exists, for listing what a directory's configuration resolves to rather than for measuring it.
© organizzolini · MIT · organizzolini/codebase