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-validategit 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-validate)<a href="https://agentmods.dev/skills/joenandez/spectre/spectre-validate"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/spectre-validate/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-validate"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/spectre-validate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
SkillSpector: 1 finding, up to low
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 →
- low Excessive Agency · line 56 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.01766 |
| Opus 5 | $0.00059 | $0.00883 |
| Sonnet 5 | $0.00023 | $0.00353 |
| Haiku 4.5 | $0.00012 | $0.00177 |
Grade A, and why
spectre-validate 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
validate
Post-implementation requirement validation. Verify the built work against scope docs and tasks.json slices, dispatch parallel validators per area, and produce one actionable gap-remediation document. Validation only — never fix.
Core principle (load-bearing)
Definition ≠ Connection ≠ Reachability. A requirement is only delivered if all three hold:
- Defined — code exists in a file.
- Connected — it is imported/called by other code.
- Reachable — a user action can trigger the code path.
Level 1 without 2/3 is dead code that happens to match the description — not complete. Always trace past "X exists" → "X is called by Z at file:line" → "Z fires when the user does W."
Inputs
$ARGUMENTS— explicit feature name/root or descendant artifact, scope docs, an explicit arbitrary plan as a requirement source, and/ortasks.jsonto validate against (paths, or "use thread context"), plus optionalexecution_state.mdfocus evidence, an immutableBASE_SHA/HEAD_SHA/DIFF_SHA256candidate tuple, and--orchestratedwhen a parent workflow owns remediation and the next step. Requirement context is REQUIRED. If absent, ask for a scope or plan path, the task detail JSON path, or "use thread context" — then wait.- Treat the plan as authoritative when passed. Otherwise use task acceptance slices, scope docs, then usable thread context. Read the authoritative source in full. For
tasks.json, extract validation slices fromphases[](parent title/description plus child acceptance criteria/context); do not useexecute.mdas the validation source except to locate the JSON path.
Working Set (late-bound — read at run-time, never inline)
- 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. - Repair stale feature/root metadata in artifacts this workflow touches.
VALIDATION_REPORT = {FEATURE_ROOT}/validation/validation_gaps.md; create its parent directory.- Read the actual code, diff, and explicitly supplied requirement artifacts just-in-time.
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 19d07a4df146
- 9d ago First seen · 77 lines · 117 tokens per session scan A 8510a3884838
spectre-validate is a skill published in the GitHub repository joenandez/spectre (158 stars, last pushed 2d ago), licensed MIT. It adds 117 tokens to every session and 1,766 once invoked, about $0.0006 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.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
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.
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…