Borrowing it
Nothing to install: this file belongs to rakovi4/continue-framework. 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/rakovi4/continue-framework/main/.claude/skills/harvest/SKILL.mdgit clone --depth 1 https://github.com/rakovi4/continue-frameworkWrote 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/rakovi4/continue-framework/harvest)<a href="https://agentmods.dev/skills/rakovi4/continue-framework/harvest"><img src="https://agentmods.dev/badge/skills/rakovi4/continue-framework/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/rakovi4/continue-framework/harvest"><img src="https://agentmods.dev/badge/skills/rakovi4/continue-framework/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 | $0.00071 | $0.01448 |
| Opus 5.5 | $0.00028 | $0.00579 |
| Sonnet 5.5 | $0.00014 | $0.00290 |
| Haiku 4.5 | $0.00007 | $0.00145 |
Grade B, and why
harvest scanned grade B with 1 finding 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 1mo 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
(`grep -F 'Tier: 2'` per file, per `.claude/templates/spec/tier-ladder.md`) whose How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/harvest — Tier 1 → Tier 2 Boundary Batch
Dispatched by /continue from the - [ ] harvest checkbox that sits between the
last Tier 1 section and the first Tier 2 one in a tier-major progress.md
(.claude/templates/workflow/progress-format.md). Untiered stories have no such
checkbox and never reach this skill.
Why a skill, not an inline /continue phase. Harvest fans out concurrent
red-agents, then stops the backend and boots a second build of the application to
baseline the result — far past what an inline gate like adapters-discovery does.
Run it inline in the main agent (like green-acceptance and the story spec
item): it dispatches its own sub-agents, which must not nest inside a wrapper agent.
What it buys. Many Tier 2 scenarios already pass the moment Tier 1 is green.
Discovering that one red-acceptance work unit at a time pays a full unit each. One
batch step runs them all at once.
Scope: acceptance level only. Only black-box-over-HTTP acceptance tests can be
pointed at a differently-built application; usecase and adapter tests compile against
production classes and cannot be baselined (CLAUDE.md). Harvest touches
acceptance/ test code and progress.md — never production code.
The batch
- Read
tests/*.mdand collect every scenario carrying an inlineTier: 2marker (grep -F 'Tier: 2'per file, per.claude/templates/spec/tier-ladder.md) whose acceptance step is not yet done. These are the harvest set. - Fan out one
red-agentper scenario, concurrently (dispatch them in a single message — layeracceptance, given the scenario name and story folder). Each runs its normal red-acceptance workflow — no harvest-special writer mode. red-agentself-partitions per its own rules:- Green as-is (the test passes the moment it is written): red-agent marks the
scenario's
red-acceptance[x]and every other step for that scenario[S]— its standard "test already passes" branch. The scenario is resolved. - Red: red-agent produces the normal disabled
red-acceptancedeliverable and the scenario continues its ordinary Tier 2 cycle later. Nothing is deleted — the red test is the start of that cycle.
- Green as-is (the test passes the moment it is written): red-agent marks the
scenario's
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.
- 1mo ago Changed · -5 lines 8069c7977de8
- 2mo ago First seen · 109 lines · 71 tokens per session scan B b4f29e195a7a
harvest is a skill published in the GitHub repository rakovi4/continue-framework (54 stars, last pushed 29d ago), licensed MIT. It adds 71 tokens to every session and 1,448 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.