Borrowing it
Nothing to install: this file belongs to joenandez/spectre. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/joenandez/spectre/main/.agents/skills/verify-spectre/SKILL.mdgit 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/verify-spectre)<a href="https://agentmods.dev/skills/joenandez/spectre/verify-spectre"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/verify-spectre/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/verify-spectre"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/verify-spectre.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 | $0.00132 | $0.01363 |
| Opus 5 | $0.00066 | $0.00681 |
| Sonnet 5 | $0.00026 | $0.00273 |
| Haiku 4.5 | $0.00013 | $0.00136 |
Grade A, and why
verify-spectre 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 11d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
verify-spectre
The gate suite for the Spectre plugin itself. Run it after any change to skills, agents, hooks, src/lib/, or the Codex mirror — and always before a release.
The reason this exists as scripts rather than a checklist: Spectre's real failures are silent. A skill whose frontmatter name drifts from its directory never triggers. A stale Codex mirror serves every Codex user the previous version indefinitely. A missing SessionStart registry or exact-load path leaves project knowledge undiscoverable without blocking the user's work. None of these break a test or throw an error — they just quietly stop working. So every check asserts an observable condition (file contents, exit code, byte-comparison) and exits nonzero. Nothing here is eyeballed.
Run it
node .agents/skills/verify-spectre/scripts/verify.mjs # gates 1-4 (default, pre-commit)
node .agents/skills/verify-spectre/scripts/verify.mjs --fast # gates 1-2 (seconds, on every change)
node .agents/skills/verify-spectre/scripts/verify.mjs --release # gates 1-5 (before publishing)
node .agents/skills/verify-spectre/scripts/verify.mjs --gate 4 # one gate, when iterating on a fix
The scripts live alongside this skill under .agents/skills/verify-spectre/scripts/ and are the single canonical copy tracked by the public repository. Keeping the executable gates beside the skill makes a fresh clone independently verifiable without relying on ignored .claude/ state.
Run from the repo root. The scripts locate the repo from their own path, so they work regardless of your working directory.
Report the PASS/FAIL summary. On failure, each check already names what was expected and what was found — quote that rather than re-deriving it.
The gates
| # | Gate | Asserts |
|---|---|---|
| 1 | structure | Skill/agent frontmatter valid and name matches its directory · expected-skills manifest intact · hooks.json parses, scripts exist, SessionStart order is bootstrap → handoff-resume → load-knowledge · no active skill contains {{REGISTRY}} · no stale fork naming · every Skill(spectre-x) / /spectre:x / @spectre:agent reference resolves · four canonical version files agree |
| 2 | tests | npm test passes; reports the test count so a silent drop (deleted tests, not fixed ones) is visible |
| 3 | codex | sync-codex --check is clean — the committed mirror matches canonical source · generated hooks reference .mjs, never .cjs, and every referenced script exists · skills rewritten to .agents/skills/ and bare skill names |
| 4 | real-cli | The CLI and hooks actually run, in throwaway temp dirs with a fresh CODEX_HOME (see below) |
| 5 | release | Clean tree · mirror in sync · versions in lockstep · tag free · GitHub authenticated |
What ships with it
7 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.
- 11d ago First seen · 61 lines · 132 tokens per session scan A d966ba846026
verify-spectre is a skill published in the GitHub repository joenandez/spectre (161 stars, last pushed 2d ago), licensed MIT. It adds 132 tokens to every session and 1,363 once invoked, about $0.0007 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.