seedbank
Skill4 starsChanged 18 days agoMITView on GitHub
Maintain a small, generated AGENTS.md of repository facts (build commands, conventions, invariants, past mistakes) that were rediscovered often or were costly to get wrong. Use at task start to check cached facts, and at task end to log and promote what you had to dig for.
In this repository5 other files it gives its agents.
- compostSkill
- greenhouseSkill
- myceliumSkill
- prunerSkill
- weederSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 21
Start: read AGENTS.md. If it answers your question, skip re-discovery.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
seedbank
!"${CLAUDE_SKILL_DIR}/bin/seedbank" mode --banner
Agents that do not expand the line above (e.g. Codex): run
<this-skill-dir>/bin/seedbank mode --banner first and follow it.
Offline fact store + profiler. It counts rediscoveries and mistake cost;
you supply the fact text and decide what to promote. Nothing is promoted
just because it was seen once; promotion is always a deliberate promote call. Formulas: references/scoring.md.
seedbank is not on PATH: always run it as <this-skill-dir>/bin/seedbank. State
lives in <git repo root>/.seedbank/.
- Start: read
AGENTS.md. If it answers your question, skip re-discovery. - While working, log only "how does this repo work" discoveries, not
every file you touch (with the plugin hook, Read/Grep/Glob and
read-only Bash such as cat/sed/grep/rg/find are logged automatically):
bin/seedbank observe run --scope <topic> -- <command...> bin/seedbank observe mistake "<rule you broke>" --scope invariants [--source <file>] bin/seedbank observe fact "<invariant>" --scope invariants - End:
bin/seedbank candidates, then
A correctness/safety invariant is always worth promoting: usebin/seedbank promote <key> --representation "<compact text>" --tier hot [--critical] bin/seedbank promote <key> --tier warm --scope <topic> bin/seedbank compile--criticalso it's protected from budget-based eviction. Promote refuses a fact contradicting one in the same scope; re-run with--replace <id>or--force.compilerewrites only the region between<!-- seedbank:begin -->/<!-- seedbank:end -->and excludes stale facts (source changed since promotion) instead of serving them as still true;--criticalfacts stay, marked "(source changed — verify)". With the plugin, a Stop hook reminds you once per session when this session produced candidates; hand the curation to thegardeneragent to keep it out of your context, or do step 3 yourself. - Existing hand-written
AGENTS.md/CLAUDE.md:bin/seedbank import <path>.
Hook setup, tiers, what to commit: references/guide.md.
Full CLI: references/schema.md.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.