Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/vinnie357/claude-skillsnpx agentmods add commands/vinnie357/claude-skills/harvestWrote 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/commands/vinnie357/claude-skills/harvest)<a href="https://agentmods.dev/commands/vinnie357/claude-skills/harvest"><img src="https://agentmods.dev/badge/commands/vinnie357/claude-skills/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/commands/vinnie357/claude-skills/harvest"><img src="https://agentmods.dev/badge/commands/vinnie357/claude-skills/harvest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00026 | $0.00747 |
| Opus 5 | $0.00013 | $0.00374 |
| Sonnet 5 | $0.00005 | $0.00149 |
| Haiku 4.5 | $0.00003 | $0.00075 |
Grade A, and why
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 7d 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.
What it actually says
Harvest implementation-agnostic feature specs from a working prototype. Spawns the pm-lead agent, which fans out discovery workers across the prototype's routes/pages, data models, integrations/dependencies/stack, and (when present) a read-only bees map; classifies findings into customer-value features versus prototype shortcuts; runs the SDLC guardrail checklist; and writes markdown spec artifacts.
What it does:
- Discovery —
pm-discoveryshards inventory routes/pages, data models, and integrations/deps/stack in parallel, plus a bees map when.bees/exists in the prototype. Pure inventory, no judgement, every entry cited to a file path. - Separation —
pm-separatorspot-verifies sampled claims, classifies each item as a customer-value feature or a prototype shortcut that must not carry forward (zero/minimal auth, hardcoded data, scale/perf assumptions), and drafts WHAT/WHY value statements that pass the portability test. - SDLC assessment —
pm-sdlc-assessorwalks the licensing/security/supportability checklist from/pm:spec-harvest'sreferences/sdlc-checklist.md, evidencing every row. - Spec generation —
pm-spec-writercomposes the feature-inventory and SDLC-assessment artifacts, then onepm-prd-authorruns per major feature area in grounded mode to produce a PRD.
Artifacts land under <OUTPUT_DIR>/: <DATE>-feature-inventory.md, <DATE>-sdlc-assessment.md, prd/<DATE>-<feature-area>.md per feature area.
Arguments:
[path-to-prototype]— absolute or relative path to the prototype repo. When omitted, ask the user where the prototype lives before doing anything else.--output=<dir>— output directory for artifacts. Defaultdocs/pm/under the prototype root.
Examples:
/pm:harvest ~/github/checkout-prototype
/pm:harvest ../checkout-prototype --output=docs/specs/
Skills the lead loads (no globs — explicit names):
/pm:spec-harvest/core:agent-loop/core:anti-fabrication/core:bees/claude-code:claude-teams
Task instructions:
Before spawning anything, ask the operator (unless already answered in the invocation): the intended production audience, any known feature areas to prioritize, and the output directory if not already given via --output. Resolve [path-to-prototype] to an absolute path relative to the current working directory. Verify the path exists (test -d) — if not, stop and report. Probe for <path>/.bees (existence only). Compute DATE as today in YYYY-MM-DD. Resolve OUTPUT_DIR to an absolute path (default <path-to-prototype>/docs/pm/).
Spawn the pm-lead subagent with PROTOTYPE_ROOT=<resolved path>, MODE=harvest, OUTPUT_DIR, DATE, and OPERATOR_ANSWERS set to the clarifying-question responses. Relay the lead's final report to the user, including the artifact paths and the confidence-tag summary.
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.
- 7d ago First seen · 42 lines · 26 tokens per session scan A b10714a7552d
harvest is a command published in the GitHub repository vinnie357/claude-skills (25 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 747 once invoked, about $0.0001 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 commands, from other repositories
template
Manage issue templates for streamlined issue creation.
sync-linear
Sync current work with Linear ticket status.
add-note
Add an internal or external note to a ConnectWise PSA ticket.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.