Borrowing it
Nothing to install: this file belongs to benwu95/prospec. 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/benwu95/prospec/main/.agents/skills/prospec-verify/SKILL.mdgit clone --depth 1 https://github.com/benwu95/prospecWrote 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/benwu95/prospec/prospec-verify)<a href="https://agentmods.dev/skills/benwu95/prospec/prospec-verify"><img src="https://agentmods.dev/badge/skills/benwu95/prospec/prospec-verify/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/benwu95/prospec/prospec-verify"><img src="https://agentmods.dev/badge/skills/benwu95/prospec/prospec-verify.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 | $0.00085 | $0.09769 |
| Opus 5.5 | $0.00034 | $0.03908 |
| Sonnet 5.5 | $0.00017 | $0.01954 |
| Haiku 4.5 | $0.00009 | $0.00977 |
Grade A, and why
prospec-verify 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 yesterday.
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 — 451 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prospec Verify Skill
Activation
When triggered, briefly describe:
- That you'll perform a comprehensive audit of the implementation
- All 5+1 verification dimensions will be checked (task completion, spec compliance, Constitution full audit, Knowledge ↔ implementation consistency, tests, and design conformance when proposal.md declares a Design Source other than
none) - That the dimensions are adjudicated by two different authorities: 1/5, 4/5 and 5/5 by the deterministic
prospec checkengine (you interpret and narrate its verdicts, you do not decide them), 2/5 and 6 by an independent fresh-context reviewer, 3/5 by both (mechanical rule inventory, judged violations) - A quality grade (S/A/B/C/D) with deployment recommendation will be provided
CLI Prerequisite (required)
The prospec CLI is a required file for this skill — its deterministic steps call
prospeccommands. Probe BEFORE any other step; there is no manual fallback.
- Run
prospec --version(Bash). - Command not found / not executable → STOP. Ask the user to install the prospec standalone
executable — the one-click installer script from the project README (macOS/Linux
install.sh, Windowsinstall.ps1) or a release binary from GitHub Releases; prospec is NOT published to npm. Then re-run this skill. - Version older than 2.10.0 → STOP. Report the installed vs required version and ask the user to upgrade, then re-run this skill.
Hand-executing a CLI-owned mutation is NEVER the fallback — that re-introduces the nondeterministic serialization this contract exists to remove.
Review/default tests use snapshot-v2 / repository-inputs-v2: working-tree content of git index members. Unchanged members and effective content preserve evidence across staging or equivalent commits. Revalidate legacy records once.
Startup Loading
- [STABLE] Read
prospec/CONSTITUTION.md— for full audit - [DYNAMIC] Read
.prospec/changes/[name]/tasks.md— task completion status - [DYNAMIC] Read
.prospec/changes/[name]/plan.md— design intent (skip forscale: quick/backfill— no plan by contract) - [DYNAMIC] Read
.prospec/changes/[name]/delta-spec.md— file specifications (skip forscale: quick— no delta-spec by contract; 2/5 isnot-applicable) - [DYNAMIC] Read
.prospec/changes/[name]/proposal.md— acceptance scenarios - [DYNAMIC] Read
.prospec/changes/[name]/metadata.yaml— current status (updated on pass; see Status Update) - [DYNAMIC] Load the Feature Spec requirements this change touches — for each REQ id the delta-spec names, run
prospec spec show <feature> --req <ids>(Bash), the**Feature:**field giving the feature. Quote them for the 2/5 comparison; never read the wholeprospec/specs/features/directory or a whole spec file — 2/5 compares this change against the REQs it touches, and one spec can run to tens of thousands of tokens of unrelated capability record. Add--story <US-N>when a REQ's surrounding story matters. An ADDED REQ is expected to be missing here: requirements graduate into the trust zone atprospec-archivePhase 3.5, so the command reports every ADDED id as unmatched and exits non-zero — that is the designed state, never a 2/5 finding. Read the MODIFIED/REMOVED ids from the spec (they exist), and take each ADDED REQ's text from the delta-spec entry itself;--story <US-N>is what shows you the section an ADDED REQ will land in. (skip forscale: quick— no delta-spec REQs to compare) - [DYNAMIC] Read
prospec/specs/product.md— understand product-level overview - [DYNAMIC] Run
prospec check --json(Bash), then read theprospec-report.jsonfile — the deterministic verdicts for Verification 1/5, 4/5 and 5/5, plus the Constitution rule inventory 3/5 audits against (the same engine the CI gate runs).--jsonwrites the file; stdout is a human-readable summary, not JSON — take structured facts from the file. Its shape (checks keyed byidunderstructural.checks[], problems understructural.findings[], freshness understructural.knowledge_health.modules[], rules understructural.constitution.rules[]) is documented inreferences/drift-report-format.md— consult it instead of reverse-engineering the JSON. The CLI is a required file (see CLI Prerequisite — a missing engine is a STOP at the probe, never a gradable state); never adjudicate a machine dimension yourself
What ships with it
6 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.
- yesterday Changed · -13 lines · +1 tokens per session 175c65fff30d
- 3d ago Changed · +2 lines 2f0c74bf1831
- 4d ago Changed · +2 lines 1e3089c7eb30
- 5d ago Changed 4c01b7af326b
- 9d ago Changed d4f721c4582a
- 11d ago Changed 5c6ebcb6b17b
- 12d ago Changed 5eb92a4ea160
- 13d ago Changed 4260653b4554
- 20d ago Changed 84ee3c019a88
- 23d ago First seen · 460 lines · 84 tokens per session scan A 76f213b52a93
prospec-verify is a skill published in the GitHub repository benwu95/prospec (6 stars, last pushed yesterday), licensed MIT. It adds 85 tokens to every session and 9,769 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.
prospec-verify compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| prospec-verifybenwu95/prospec | Skill | 6 | yesterday | MIT | A | 85 | Claude Code, Codex |
| ospec-goalclawplays/ospec | Skill | 390 | 2mo ago | MIT | A | 29 | Codex |
| ospecclawplays/ospec | Skill | 390 | 2mo ago | MIT | A | 26 | Claude Code, Codex |
| ospec-changeclawplays/ospec | Skill | 390 | 2mo ago | MIT | A | 18 | Codex |
| review-spdzhu1090093659/spec_driven_develop | Skill | 993 | 3mo ago | MIT | A | 72 | Claude Code |
| code-reviewdanweinerdev/claude-sdd-planner | Skill | 2 | 1mo ago | MIT | A | 38 | Claude Code |
| sdd-code-reviewdanweinerdev/claude-sdd-planner | Skill | 2 | 1mo ago | MIT | A | 28 | Claude Code |