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-provegit 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-prove)<a href="https://agentmods.dev/skills/joenandez/spectre/spectre-prove"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/spectre-prove/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-prove"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/spectre-prove.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 | $0.00061 | $0.01698 |
| Opus 5 | $0.00030 | $0.00849 |
| Sonnet 5 | $0.00012 | $0.00340 |
| Haiku 4.5 | $0.00006 | $0.00170 |
Grade A, and why
spectre-prove 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
prove
Prove the completed experience against its approved contract. Reports, tests, assertions, and developer claims are leads; observable behavior and reviewed evidence decide.
Inputs
$ARGUMENTS- optional explicit feature name/root or descendant artifact, explicitly passed source-plan path, scope/UX/prototype/test-guide paths, journey hints, fresh inspected evidence to reuse, an authorized scope hash, and--orchestratedwhen a parent owns the next action.- Optional
--profile focused, valid only with--orchestrated: use existing proof tools/scenarios only, run no tooling research or dependency-selection gate, and record unavailable proof capability asPARTIALwith limitationPROOF_TOOLING_UNAVAILABLE. - Resolve an explicit feature/root, descendant, or unambiguous thread artifact; otherwise derive a concise kebab name and proceed without a naming gate.
- 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 acceptance truth in this order: current explicit user instruction; an explicitly passed source plan as an acceptance source; approved scope and UX/prototype; task acceptance criteria; test guide. Derivative execution evidence such as
execution_state.mdmay focus proof but is not acceptance truth. Surface contradictions before proving against an invented interpretation.
This skill must work in a fresh session. Read canonical artifacts and live repository state instead of relying on prior conversation.
Each invocation is exactly one proof pass. Derive a candidate key from relevant product inputs, scope hash, and scenario/config definitions; record observed start/finish state excluding generated proof. If product state changes, mark affected rows PARTIAL with PROOF_STATE_CHANGED; never bind proof to a future candidate.
What ships with it
3 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 Changed · +2 lines d1d31fbcb9ec
- 7d ago Changed ad3e76417761
- 12d ago First seen · 86 lines · 61 tokens per session scan A 23fe2f3072d9
spectre-prove is a skill published in the GitHub repository joenandez/spectre (161 stars, last pushed 3d ago), licensed MIT. It adds 61 tokens to every session and 1,698 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
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.