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 vinnie357/claude-skills --skill spec-harvestgit clone --depth 1 https://github.com/vinnie357/claude-skillsWrote 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/vinnie357/claude-skills/spec-harvest)<a href="https://agentmods.dev/skills/vinnie357/claude-skills/spec-harvest"><img src="https://agentmods.dev/badge/skills/vinnie357/claude-skills/spec-harvest/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/vinnie357/claude-skills/spec-harvest"><img src="https://agentmods.dev/badge/skills/vinnie357/claude-skills/spec-harvest.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 | $0.00069 | $0.01559 |
| Opus 5 | $0.00034 | $0.00779 |
| Sonnet 5 | $0.00014 | $0.00312 |
| Haiku 4.5 | $0.00007 | $0.00156 |
Grade A, and why
spec-harvest 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 8d 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.
Spec Harvest
Extracts a customer-value feature inventory, an SDLC risk assessment, and per-feature PRDs from a working prototype — without carrying the prototype's implementation choices into the spec. /pm:harvest runs all four phases end-to-end via an agent team; /pm:assess runs phase 3 alone against an existing inventory.
Four Phases
- Discovery — pure inventory, no judgment. Record what is observed: routes/pages, data models, external integrations, dependencies, technology stack and framework choices. Every entry carries a confidence tag (see Anti-Fabrication below).
- Separation — split discovery findings into (a) customer-value features: behaviors users actually want regardless of implementation — what a user can do, what data shapes and interactions matter, what outcomes the user cares about; and (b) prototype shortcuts that must NOT carry forward: zero/minimal authentication, hardcoded data, scale/performance assumptions.
- SDLC assessment — run
references/sdlc-checklist.mdagainst the prototype: licensing, security, supportability./pm:assessinvokes this phase standalone. - Spec generation — three artifact types: the feature inventory (
templates/feature-inventory.md), the SDLC assessment (templates/sdlc-assessment.md), and one PRD per major feature area authored via/pm:prdin grounded mode.
Team Shape
| Agent | Model | Phase | Responsibility |
|---|---|---|---|
| pm-lead | opus | all | Orchestrates the team, sequences phases, aggregates worker reports. |
| pm-discovery | haiku | 1 | Runs one of four inventory shards: routes-pages, data-models, integrations-deps-stack, bees-map. |
| pm-separator | sonnet | 2 | Splits discovery output into customer-value features vs. prototype shortcuts. |
| pm-sdlc-assessor | sonnet | 3 | Runs the SDLC checklist, produces risk findings. |
| pm-spec-writer | sonnet | 4 | Writes the feature inventory and SDLC assessment artifacts. |
| pm-prd-author | sonnet | 4 | Authors one PRD per major feature area via /pm:prd. |
What ships with it
5 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.
- 8d ago First seen · 88 lines · 69 tokens per session scan A 316a1a87832e
spec-harvest is a skill published in the GitHub repository vinnie357/claude-skills (25 stars, last pushed 2d ago), licensed MIT. It adds 69 tokens to every session and 1,559 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 2026-09-03.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.