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 skills add joenandez/spectre --skill spectre-prunegit clone --depth 1 https://github.com/joenandez/spectreWrote 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/joenandez/spectre/spectre-prune)<a href="https://agentmods.dev/skills/joenandez/spectre/spectre-prune"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/spectre-prune/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/joenandez/spectre/spectre-prune"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/spectre-prune.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00078 | $0.01096 |
| Opus 5 | $0.00039 | $0.00548 |
| Sonnet 5 | $0.00016 | $0.00219 |
| Haiku 4.5 | $0.00008 | $0.00110 |
Grade A, and why
spectre-prune 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
prune
Find and remove dead code/artifacts from recent work. Conservative by default: investigate and validate before deleting; uncertain items stay in place and are reported in-thread.
Inputs
$ARGUMENTS— optional scope. Acommit_id/SHA,unstaged/staged,context/session, a scoped file list, or--orchestratedwhen a parent workflow owns the next step. If ambiguous -> ask which scope mode. If a providedcommit_idis invalid or not in history -> stop and ask for a valid ref.FEATURE_ROOT— explicit feature name/root or one descendant feature artifact.
Working Set
- Reuse a managed
FEATURE_ROOTonly when explicit/current-thread evidence ties it to this work (physical directory wins; never branch/recency/lifecycle/scans); distinct work ignores ambient roots. Otherwise, including on collision, standalone MUST first load and followSkill(spectre-feature-root)through DONE; orchestrated calls escalate. Keep writes beneath it and pass it unchanged. - Resolve scope late at runtime:
- commit_range: union of committed files from
{commit_id}^..HEAD(including the commit), staged, unstaged, and untracked. Ifcommit_id == HEAD, use staged + unstaged + untracked. - unstaged/staged: union of staged + unstaged + untracked.
- context: ask for the session files and wait.
- commit_range: union of committed files from
- Respect
.gitignore, package/tsconfig context, generated-file boundaries, and repo-local conventions. Paths are repo-root relative in reports.
Outputs + DONE
- Confirmed-safe cleanup edits only; in orchestrated mode, production/source only—never tests/fixtures.
- Compact in-thread summary: safe removals (
file:line, what, why safe), manual review, exclusions, impact, ESLint-debt notes. Write no cleanup/evidence artifact. - DONE when: every removed item was validated
CONFIRMED_SAFE; everyUNCERTAIN/UNSAFEitem remains untouched and appears in Manual Review; standalone affected checks pass or a failed cleanup edit is rolled back; no--no-verify,eslint-disable,@ts-ignore, or@ts-expect-errorwas introduced; and the in-thread summary is complete.
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 Changed · +2 lines 7ae59b2931bb
- 7d ago Changed · +1 lines · -29 tokens per session d038887cfaf5
- 12d ago First seen · 57 lines · 107 tokens per session scan A c105ad06ff9d
spectre-prune is a skill published in the GitHub repository joenandez/spectre (161 stars, last pushed 3d ago), licensed MIT. It adds 78 tokens to every session and 1,096 once invoked, about $0.0004 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…