Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add melodic-software/claude-code-plugins/plugin install code-metricsWrote 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/melodic-software/claude-code-plugins/audit-complexity)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/audit-complexity"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/audit-complexity/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/audit-complexity"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/audit-complexity.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00101 | $0.02589 |
| Opus 5.5 | $0.00040 | $0.01036 |
| Sonnet 5.5 | $0.00020 | $0.00518 |
| Haiku 4.5 | $0.00010 | $0.00259 |
Grade A, and why
audit-complexity 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 4d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-computed context
Current branch: !git branch --show-current 2>/dev/null || echo "unknown"
Purpose
Complexity is the measure with the most citable reference on the operator's list and the most folklore around it. This skill reports the numbers, per function where the collector reports per function, beside references whose provenance is printed with them, and stops there: no pass or fail, no severity, no finding. Whether a complexity of 23 is worth changing is the reader's call.
Collectors are tried in order per lane and the first that resolves is used. Nothing is installed, downloaded, or fetched at run time; a lane with no resolvable collector reports that in the run table and the other lanes still run.
| Lane | Cyclomatic | Cognitive | Halstead difficulty |
|---|---|---|---|
| TypeScript/JavaScript | lizard, then ESLint's core complexity rule |
eslint-plugin-sonarjs |
multimetric, per file |
| Python | lizard, then radon cc -j |
no maintained collector found; the row says so | radon hal -j, per function, then multimetric |
| Bash | shellmetrics, then multimetric |
no collector found; the row says so | multimetric, per file |
| Go | lizard, then gocyclo |
gocognit |
multimetric, per file |
| C# | deferred | deferred | deferred |
lizard and radon report a start and an end line per function; gocyclo, gocognit,
shellmetrics, and the two ESLint rules report a start line only, and their rows are labeled
start-line-only. multimetric has no per-function granularity at all, so its rows are per file,
carry function: null, and are labeled file-level. Its Bash cyclomatic figure is labeled
multimetric-approximation because it under-counts against a per-function parser.
Run it
"${CLAUDE_SKILL_DIR}/scripts/audit-complexity.sh" # the change: merge-base diff plus uncommitted files
"${CLAUDE_SKILL_DIR}/scripts/audit-complexity.sh" src/ lib/parse.py # explicit paths (a missing one is a usage error)
"${CLAUDE_SKILL_DIR}/scripts/audit-complexity.sh" --all # every tracked or untracked-but-not-ignored file
"${CLAUDE_SKILL_DIR}/scripts/audit-complexity.sh" --json --all src/ # the code-metrics/v2 document instead of markdown
What ships with it
3 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.
- 4d ago Changed 959a0f95820c
- 12d ago Changed 867cb7843542
- 15d ago Changed 05081880e603
- 16d ago Changed 7fecdc12a4ad
- 17d ago Changed · -151 tokens per session eea0a215ded5
- 23d ago Changed b58369249cbd
- 1mo ago Changed · +1 lines a6b68add6e49
- 1mo ago Changed · +26 lines d72fc2a7d43f
- 1mo ago Changed · +7 lines · -8 tokens per session f3299359d0e2
- 1mo ago First seen · 122 lines · 260 tokens per session scan A 292569d158e1
audit-complexity is a skill published in the GitHub repository melodic-software/claude-code-plugins (25 stars, last pushed today), licensed MIT. It adds 101 tokens to every session and 2,589 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-06.
Other skills, from other repositories
parallel-orchestrator
Manage parallel Claude Code workstreams using git worktrees. Use when: splitting large tasks across multiple workers, coordinating parallel development, monitoring worker progress, integrating completed work, analyzing work item documents (code reviews, issue lists). Triggers: parallel, orchestrator, worktrees…
parallel-worker
Execute focused implementation tasks in a parallel workflow. Use when: working on assigned files in a worktree, making checkpoint commits, signaling dependencies or blockers, completing orchestrator-assigned tasks. Triggers: worker, checkpoint, worktree, assigned scope, commit prefix, parallel task.
optimize-local-search
For NP-hard optimization: TSP, scheduling, assignment problems. Uses greedy construction + local improvement (2-opt, hill climbing).
pass-function-as-arg
For generic algorithms: strategy pattern, callbacks, configurable behavior. Pass functions as parameters to customize algorithm behavior.
solve-constraint-puzzle
For constraint satisfaction: Sudoku, scheduling, N-queens, logic puzzles, SAT-like problems, assignment problems. Uses propagate-then-search pattern.
test-with-examples
For example-driven development: test cases as specifications, input/output pairs, documentation through examples.