Agent skill

Harvest

by huytieu in huytieu/COG-second-brain

Capture durable session learnings, stage for human promotion to 05-knowledge/lizard, and propose skill/CLAUDE.md patches.

MITAuto-check passedAgent Workflows

Install Harvest

skills CLI
$ npx skills add huytieu/COG-second-brain --skill harvest -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install huytieu/COG-second-brain harvest --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/huytieu/COG-second-brain.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/harvest .claude/skills/harvest && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
harvest
GitHub stars
1.3k
Token cost
~609 tokens
SKILL.md length
215 words
Files
1
Skills in repo
37
Repo updated
First seen
Licence
MIT

At a glance

Capture durable session learnings, stage for human promotion to 05-knowledge/lizard, and propose skill/CLAUDE.md patches.

  • Works in 3 steps: Collect (automatic or manual) → Curate (/harvest promote) → Retro line
  • Tasks that involve Agent instruction files
  • SKILL.md covers Triggers, Phase 1 — Collect (automatic…, Phase 2 — Curate (/harvest… and Phase 3 — Retro line, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Harvest is an agent skill from huytieu/COG-second-brain. Capture durable session learnings, stage for human promotion to 05-knowledge/lizard, and propose skill/CLAUDE.md patches. Triggered by /harvest, SessionEnd hook staging, or nightly enhance. Never writes durable knowledge without your approval.

Its SKILL.md is about 610 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Agent instruction files. The repository describes itself as: Self-evolving second brain with 35 AI skills, 10 agents, and people CRM. Closed-loop harness: a V-model verification lifecycle where the worker never grades its own homework… The licence is MIT.

When your agent uses it

  • Tasks that involve Agent instruction files

Example prompts

  • “/harvest”

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Collect (automatic or manual)
  2. Curate (/harvest promote)
  3. Retro line

What it can do on your machine

Read from SKILL.md and the folder at commit 36ac9d7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Harvest loads about 609 tokens when it runs. Until then it costs about 63 tokens; SKILL.md has 215 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~63
When it runs · the whole SKILL.md, loaded when a task matches
~609

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from huytieu/COG-second-brain at commit 36ac9d7, republished under its MIT licence (© huytieu). 215 words, ~609 tokens.

Download SKILL.mdSave it as .claude/skills/harvest/SKILL.md (or your agent's skills folder).
name
harvest
description
Capture durable session learnings, stage for human promotion to 05-knowledge/lizard, and propose skill/CLAUDE.md patches. Triggered by /harvest, SessionEnd hook staging, or nightly enhance. Never writes durable knowledge without your approval.

/harvest — session learning capture

Adapted from dwarves-kit harvest hook + vault lizard pipeline. Prevents tacit knowledge dying in the transcript.

Triggers

  • /harvest — manual end-of-session
  • /harvest promote — curate staging → lizard drafts (uses harvest-curator)
  • Staging file written by stop hook (.cursor/hooks/harvest-stager.sh)

Phase 1 — Collect (automatic or manual)

Scan the current session for:

  1. Corrections you made ("no, actually X", rejected deliverables)
  2. New stable facts (IDs, URLs, decisions) not yet in 05-knowledge
  3. Process lessons (what worked, what failed, friction)
  4. Skill gaps (something that should be a Verify step or CLAUDE.md rule)

Append to 04-projects/harness/harvest/staging-<YYYY-MM-DD>.md:

markdown
## <HH:MM> — <trigger>
- type: correction|fact|process|skill-gap
- source: <file or "session">
- text: <one paragraph max>
- proposed_home: <path or "new lizard note">

Dedup: skip if same fact already in staging today or in 05-knowledge.

Phase 2 — Curate (/harvest promote)

Spawn harvest-curator (Sonnet). It writes /tmp/harvest-curate-<date>.md.

Lead (Opus) presents to the user:

  • Promote list → approve which become 05-knowledge/lizard/YYYY-MM-DD-<slug>.md
  • Fold list → approve inline edits to existing notes
  • Skill patches → approve CLAUDE.md / SKILL.md diffs

Only after approval: write durable files. Update 05-knowledge/lizard/index.md.

Phase 3 — Retro line

One line to 01-daily/journal/<today>.md:

Harvest: <n> staged, <m> promoted, <k> folded

Rules

  • Harvest is advisory. It never auto-writes 05-knowledge.
  • Contradictions with existing knowledge → flag both, ask the user.
  • Pair with /memory-hygiene monthly for environment-dependent facts in ~/.claude/.../memory/.

Nightly enhance (optional)

If you want harvest to run unattended, schedule a job that invokes the skills in this order. There is nothing to install first, since COG ships no hooks.

/memory-hygiene
/harvest promote     # only if the staging file is non-empty
/content-factory     # only if scheduled

© huytieu, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/harvest of huytieu/COG-second-brain.

Open the folder on GitHubat commit 36ac9d7

Compare with similar skills

Harvest next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Harvest compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Harvest this skillhuytieu/COG-second-brain1.3k—~609Automated safety check: PassMIT
Using Agent Skillsaddyosmani/agent-skills105k4 repos~2.4kAutomated safety check: PassMIT
Claude ReflectBayramAnnakov/claude-reflect1.8k2 repos~627Automated safety check: PassMIT
Writing For Agentsbestofjs/bestofjs3.1k20 repos~2.7kAutomated safety check: PassMIT
Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills21k—~1.9kAutomated safety check: PassMIT
Task Observerrebelytics/one-skill-to-rule-them-all3.2k1 repos~11kAutomated safety check: PassCC-BY-4.0

Similar skills

  • Using Agent Skills

    addyosmani/agent-skills

    Meta-skill for choosing which workflow skill fits the task at hand, plus always-on habits: surface assumptions, stop on confusion, push back, keep it simple and stay in scope.

    105k GitHub starsUsed in 4 repos~2.4k tokens
    Agent WorkflowsAuto-check passed
  • Claude Reflect

    BayramAnnakov/claude-reflect

    Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md.

    1.8k GitHub starsUsed in 2 repos~627 tokens
    Agent WorkflowsAuto-check passed
  • Writing For Agents

    bestofjs/bestofjs

    Writing documents for agents. An agent skill from bestofjs/bestofjs.

    3.1k GitHub starsUsed in 20 repos~2.7k tokens
    Agent WorkflowsAuto-check passed
  • Neat-Freak Knowledge Closeout

    KKKKhazix/khazix-skills

    Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.

    21k GitHub stars~1.9k tokensUpdated 9 days ago
    Agent WorkflowsAuto-check passed
  • Task Observer

    rebelytics/one-skill-to-rule-them-all

    Monitors task execution for skill improvement opportunities.

    3.2k GitHub starsUsed in 1 repo~11k tokens
    Agent WorkflowsAuto-check passed
  • SkillOpt Sleep Cycle

    microsoft/SkillOpt

    Official

    Runs an on-demand or nightly sleep cycle that reviews past Claude Code sessions and proposes validated updates to CLAUDE.md and skills.

    18k GitHub stars~2.3k tokensUpdated 4 days ago
    Agent WorkflowsAuto-check passed

More from huytieu/COG-second-brain

All 37 skills in this repo
  • Voice Baseline

    huytieu/COG-second-brain

    Measure your own writing corpus for the words and sentence shapes you over-use, so an agent writing in your voice stops amplifying your tics into a style.

    1.3k GitHub stars~957 tokensUpdated 8 days ago
    Auto-check passed
  • Daily Journal

    huytieu/COG-second-brain

    A passive daily work journal that Claude keeps FOR you so you never have to write it yourself.

    1.3k GitHub stars~1.3k tokensUpdated 8 days ago
    Auto-check passed
  • Editorial Illustrations

    huytieu/COG-second-brain

    Generate meaning-carrying editorial data-illustrations in the monotykamary / Linear aesthetic (near-black grayscale, Inter display + mono labels, hairline framed figures) with a single coral accent.

    1.3k GitHub stars~2.4k tokensUpdated 8 days ago
    Auto-check passed
  • Loop Engineering

    huytieu/COG-second-brain

    Shared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns.

    1.3k GitHub stars~1.5k tokensUpdated 8 days ago
    Auto-check passed
  • Release Video

    huytieu/COG-second-brain

    Turn a product release (the list of shipped items plus real screen recordings) into a motion recap video and one explained demo per feature, with sound effects tied to on-screen motion and a…

    1.3k GitHub stars~1.7k tokensUpdated 8 days ago
    Auto-check passed
  • Onboarding

    huytieu/COG-second-brain

    Personalize COG for your workflow - creates profile, interests, and watchlist files with guided setup (run this first!)

    1.3k GitHub starsUsed in 1 repo~3.1k tokens
    Auto-check passed

Categories

Questions about Harvest

What does Harvest do?

Capture durable session learnings, stage for human promotion to 05-knowledge/lizard, and propose skill/CLAUDE.md patches. Harvest is an agent skill from huytieu/COG-second-brain.md patches.

When should I use Harvest?

Harvest fits situations like: tasks that involve Agent instruction files.

How do I install Harvest in Claude Code?

Run `npx skills add huytieu/COG-second-brain --skill harvest -a claude-code`. Or copy the skill folder (skills/harvest in huytieu/COG-second-brain) into .claude/skills/harvest in your project. Claude Code loads it when a task matches its description.

How do I install Harvest in Codex?

Run `npx skills add huytieu/COG-second-brain --skill harvest -a codex`. Or copy the skill folder (skills/harvest in huytieu/COG-second-brain) into .agents/skills/harvest in your project. Codex loads it when a task matches its description.

Can I use Harvest in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add huytieu/COG-second-brain --skill harvest -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/harvest, .gemini/skills/harvest, .github/skills/harvest and .opencode/skills/harvest in your project.

What does Harvest need to run?

SKILL.md names no scripts, command-line tools or credentials: Harvest is instructions for the agent only.

Does Harvest access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Harvest safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Harvest use?

Harvest is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Harvest use?

About 609 tokens (SKILL.md is roughly 2.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Harvest?

Skills that share tags, products or a category with Harvest: Using Agent Skills (addyosmani/agent-skills, 105k stars), Claude Reflect (BayramAnnakov/claude-reflect, 1.8k stars), Writing For Agents (bestofjs/bestofjs, 3.1k stars) and Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Harvest?

huytieu (a GitHub user) maintains it in huytieu/COG-second-brain, which has 1,268 GitHub stars. The repository holds 37 skills in this directory. The repository was last updated on October 2, 2026.

Source: huytieu/COG-second-brain on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.