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-type-debt)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/audit-type-debt"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/audit-type-debt/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-type-debt"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/audit-type-debt.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 | $0.00117 | $0.02554 |
| Opus 5.5 | $0.00047 | $0.01022 |
| Sonnet 5.5 | $0.00023 | $0.00511 |
| Haiku 4.5 | $0.00012 | $0.00255 |
Grade A, and why
audit-type-debt 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 — 144 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
"Get any and unknown to zero" is a goal without a yardstick: no standard and no CWE anchors a
typed-code percentage. This skill reports what the two tools that produce a real percentage
measure, per file and per lane, and says plainly where the number comes from and what it does not
mean. There is no pass or fail here, and no bar to argue with.
| Lane | Collector | Values | The number it reports |
|---|---|---|---|
| TypeScript/JavaScript | type-coverage |
lane row: type_coverage_pct, typed_identifiers, total_identifiers, any_count; file row: any_count alone, the other three null |
identifiers whose type is not any, over all identifiers |
| Python | mypy --any-exprs-report |
type_coverage_pct, any_expressions, expressions_total on every file row and on the lane row |
mypy's own Coverage column: expressions not typed Any, over all expressions |
| Bash | not applicable | no collector reports a typed-code ratio for shell | |
| Go | not applicable | the compiler admits no untyped identifier to count | |
| C# | not applicable | no tool produces a comparable percentage for C#; a dynamic/object occurrence count is not comparable to a ratio |
Run it
"${CLAUDE_SKILL_DIR}/scripts/audit-type-debt.sh" # the change: diff from the merge-base plus uncommitted files
"${CLAUDE_SKILL_DIR}/scripts/audit-type-debt.sh" src/ lib/api.py # explicit paths (a missing one is a usage error)
"${CLAUDE_SKILL_DIR}/scripts/audit-type-debt.sh" --all # every tracked or untracked-but-not-ignored file
"${CLAUDE_SKILL_DIR}/scripts/audit-type-debt.sh" --json --all src/ # the code-metrics/v2 document instead of markdown
Present the markdown report as printed. It opens with the scope and a "Coverage of this run" table
(lane, collector, status, reason), then the reference with its provenance and layer, then one row
per file, least typed first, and one row per lane labeled lane-total. Keep the --json
document when the numbers feed a comparison:
/verification:measure metrics consumes it when the verification plugin is installed (treat a
report whose status is empty on either side as INCONCLUSIVE); otherwise keep the JSON beside
your notes and compare by hand.
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 · +1 lines 08a1bc08dca2
- 16d ago Changed d8189907e92f
- 17d ago Changed · +3 lines · -118 tokens per session a49708f0c39d
- 23d ago Changed b1668e1715a9
- 1mo ago Changed · +39 lines · +3 tokens per session e50bde98e922
- 1mo ago Changed · -1 tokens per session 2e8d6925e225
- 1mo ago Changed · +5 lines 67a2b333611d
- 1mo ago First seen · 96 lines · 233 tokens per session scan A c2797541b0fc
audit-type-debt is a skill published in the GitHub repository melodic-software/claude-code-plugins (25 stars, last pushed today), licensed MIT. It adds 117 tokens to every session and 2,554 once invoked, about $0.0005 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
cache-recursive-calls
For dynamic programming: overlapping subproblems, recursive solutions with repeated computations, memoization to avoid redundant work.
intern-symbols-identity
For fast comparison: ensure only one instance of each symbol, use 'is' instead of '==', symbol tables for interpreters.
iterate-with-itertools
For combinatorial iteration: permutations, combinations, cartesian products, without storing all results in memory.
overload-operators-dsl
For domain-specific languages: operator overloading, make Python look like math/domain notation, expression builders.
parse-extract-input
For text processing: extract numbers, words, structured data from messy text using regex patterns, parsing utilities.
pass-function-as-arg
For generic algorithms: strategy pattern, callbacks, configurable behavior. Pass functions as parameters to customize algorithm behavior.