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-sweepgit 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-sweep)<a href="https://agentmods.dev/skills/joenandez/spectre/spectre-sweep"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/spectre-sweep/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-sweep"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/spectre-sweep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 9 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00070 | $0.00990 |
| Opus 5 | $0.00035 | $0.00495 |
| Sonnet 5 | $0.00014 | $0.00198 |
| Haiku 4.5 | $0.00007 | $0.00099 |
Grade A, and why
spectre-sweep 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sweep
Prepare uncommitted or recently-changed work for check-in: a fast, formulaic hygiene pass, then descriptive conventional commits. No subagents, no approval gates — execute each step and move on.
Inputs
$ARGUMENTS(optional scope/intent hint, compact Prune/Test check results, plus--orchestratedwhen a parent owns the next step). Read the live working tree at runtime (git status,git diff) — do not assume a prior phase ran.
Working Set
Changed files only. Opportunistic, not forensic — do not hunt beyond the diff.
Outputs + DONE
One or more conventional commits covering the changes. Sweep is the sole pre-rebase commit owner in orchestrated Ship/Clean mode. DONE when:
- Diff reviewed: no unintended edits, no out-of-scope staged files, no secrets/keys/credentials/PII.
- Debug/temp logging removed; intentional logs (errors, key state transitions) kept at production-appropriate levels.
- Commented-out code, session-introduced TODO/FIXME/HACK, and hardcoded test values resolved or documented.
- Lint passes with zero violations fixed by suppression — refactor structural issues, never
eslint-disableor equivalent..gitignorecovers temp/build/IDE artifacts. - Stale/uncovered integrated lint/typecheck/build/related checks have no branch-caused failure; unrelated findings are recorded/routed.
- Staging includes canonical specs/research/decisions/final reviews,
bug-report.md, and requiredproof/proof.json+proof/proof.html, but excludes Execute evidence, verification reports, checkpoints, runs, markers, working-set/cleanup summaries, and local lifecycle state. Product/CI-consumed qualification artifacts belong at product-owned paths and may be staged. - Work committed as
type(scope): descriptionconventional commits, split by concern.
Method / guardrails
- Diff sanity and artifact tenancy — scan the full diff for accidental edits, stray staged files, secrets, and local lifecycle residue. Ensure local artifact patterns are ignored; never stage or commit them.
- Log + code hygiene — strip debug logging, commented-out code, leftover TODO/FIXME from this work, hardcoded test values; keep intentional logs.
- Opportunistic dead code (changed files only) — orphaned imports, unused vars/functions, debugger statements. No deep investigation.
- Strict lint — fix all violations by correcting code; YOU MUST NOT suppress or
--no-verify. Refactor for size/complexity thresholds. - Integrated verification — use received compact Prune/Test results to run only stale/uncovered lint/typecheck/build/related tests across demonstrated dependency boundaries. Never run a repository-wide baseline or full suite. A failure is repair or routing work, not a blocker: fix branch-caused failures and reverify; record/route unrelated failures and continue; reproduce only the failing check/test at the base SHA when attribution is indeterminate. Do NOT author new tests — this is a sweep, not a test pass.
- Commit — group by concern into conventional commits.
- Types: feat · fix · refactor · test · chore · docs · style · perf.
- Subject answers what changed and why; include scope (
feat(auth): add token refresh on 401). Optional body for motivation/trade-offs. - One concern per commit — if it spans concerns, split it. Treat commits as durable context for future readers/LLMs; never
fix: updates/refactor: clean up.
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 · +7 lines 0341909815d0
- 7d ago Changed · -61 tokens per session 4b9a5a84a15c
- 12d ago First seen · 45 lines · 131 tokens per session scan A 01f3b4eec8dd
spectre-sweep is a skill published in the GitHub repository joenandez/spectre (161 stars, last pushed 3d ago), licensed MIT. It adds 70 tokens to every session and 990 once invoked, about $0.0003 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
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
github-automation
GitHub workflow automation, PR management, issue tracking, and code review coordination. Integrates with GitHub Actions and repository management. Use when: PR creation, code review, issue management, release automation, workflow setup. Skip when: local-only changes, non-GitHub repositories.
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
github-contributor
End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…