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/melodic-software/claude-code-plugins/scannpx skills add melodic-software/claude-code-plugins --skill scangit clone --depth 1 https://github.com/melodic-software/claude-code-pluginsWhat 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 | $0.00244 | $0.03928 |
| Opus 5 | $0.00122 | $0.01964 |
| Sonnet 5 | $0.00049 | $0.00786 |
| Haiku 4.5 | $0.00024 | $0.00393 |
Grade A, and why
scan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-computed context
Current branch: !git branch --show-current 2>/dev/null || echo "unknown"
Recent commits: !git log --oneline -10 2>/dev/null || echo "no history (shallow or fresh clone)"
Shallow clone: !git rev-parse --is-shallow-repository 2>/dev/null || echo "unknown"
Lane config: !ls "${CLAUDE_PROJECT_DIR:-.}/.claude/bugs.md" 2>/dev/null || echo "absent — bundled default lanes apply"
Variables
Arguments: $ARGUMENTS
Purpose
/bugs:scan is the front of the bug lifecycle: it hunts defects nobody has observed yet, in
code that is resting. Every other finding-producer in reach needs an oracle first, a diff, a failing
test, a stack trace, a factual claim, a comment marker. This one needs none of them.
One invocation is one bounded pass: hunt a target (or a rotated lane), verify each candidate
through a separate fresh-context gate, report what survives in the plugin's five-field shape, stop.
That makes it equally usable interactively ("find a bug in the billing module"), from a /loop, or as
a daily operator routine, the same bounded unit either way.
The design premise, taken from published practice: per-run recall is low and the raw false-positive rate is high, so recall and precision are separated into two stages. Hunters are told to be generous; the verification gate is told to refute. A finding that reaches the report survived an agent whose job was to kill it.
Verb contract. Read-only toward the repository
Bare invocation is read-only: it never edits code, never branches, never pushes, never files a
tracker item. Filing sits behind --track, and model auto-invocation never supplies --track on its
own. A user (or a standing lane rule) must ask for it.
Reconciliation: persisting the findings report and its cursor block under ${CLAUDE_PLUGIN_DATA}
is plugin-owned state, not target-repo mutation. The scanned repository's working tree, index, and
history are untouched by a bare run. --dry-run goes further: it emits the findings to stdout and
persists nothing. No report file, no cursor advance, no filing.
What ships with it
4 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.
- 2d ago First seen · 246 lines · 244 tokens per session scan A cba621895072
scan is a skill published in the GitHub repository melodic-software/claude-code-plugins (12 stars, last pushed 2d ago), licensed MIT. It adds 244 tokens to every session and 3,928 once invoked, about $0.0012 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 2026-08-30.
Other skills, from other repositories
deep-research
Conducts iterative deep research on any topic using web search, progressive exploration, and structured synthesis. Use when asked for comprehensive research, deep investigation, thorough analysis, or multi-source exploration of any topic. Triggers: research, investigate, deep dive, comprehensive analysis, explore…
error-ux
Principles and patterns for writing error messages that help users recover. Use when auditing, writing, or improving error messages in code. Triggers: error messages, user experience, error handling, exception messages, validation errors.
adversarial-patterns
Library of realistic adversarial attack vectors and anti-patterns to avoid. Contains examples of valid attacks and subtle gaming patterns to reject.
documentation-testing
Provides heuristics for identifying incomplete or broken documentation. Use when validating README setup instructions, testing onboarding flows, or auditing documentation quality. Triggers: docs, readme, onboarding, setup validation, documentation audit.
adversarial-analysis
Analyze code to identify explicit contracts, implicit usage patterns, and realistic boundary conditions. Contains concrete formulas for calculating input realism limits. Use before generating adversarial tests.
propagate-then-search
For constraint problems: eliminate impossibilities before guessing, reduce search space through inference, fail fast on contradictions.