oliverweissl/context-garden / skills/seedbank
seedbank
VerifiedMaintain 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.
| File | Kind | Size |
|---|---|---|
| .gitignore | other | 40 B |
| SKILL.md | skill md | 2.7 KB |
| agents/gardener.md | markdown | 1.6 KB |
| bin/seedbankexecutable | script | 1.2 KB |
| references/guide.md | markdown | 3.3 KB |
| references/schema.md | markdown | 5.4 KB |
| references/scoring.md | markdown | 2.1 KB |
| scripts/cg_fingerprint.py | script | 3.1 KB |
| scripts/cg_mode.py | script | 5.4 KB |
| scripts/sb_compile.py | script | 5.6 KB |
| scripts/sb_conflicts.py | script | 2.3 KB |
| scripts/sb_hook.py | script | 13.5 KB |
| scripts/sb_scoring.py | script | 3.4 KB |
| scripts/sb_store.py | script | 9.3 KB |
| scripts/seedbank.pyexecutable | script | 43.0 KB |
| tests/fixtures/mini_repo/CMakeLists.txt | markdown | 94 B |
| tests/fixtures/mini_repo/README.md | markdown | 126 B |
| tests/fixtures/mini_repo/src/generated/bindings.cpp | other | 92 B |
| tests/fixtures/mini_repo/tools/codegen.py | script | 57 B |
| tests/smoke_test.shexecutable | script | 29.7 KB |
agents/gardener.md
View on GitHub---
name: gardener
description: Curates seedbank at the end of a task: reviews this session's promotion candidates, writes compact fact text, promotes what is worth caching and recompiles AGENTS.md. Use when the seedbank Stop reminder fires or after a task that needed a lot of digging.
tools: Bash, Read
skills: [seedbank, context-garden:seedbank]
model: sonnet
maxTurns: 25
---
You curate the repository's seedbank and nothing else. The seedbank skill
is preloaded; if its banner says it is off or manual, stop and report that.
If the task names a repo (a session started in a folder of many repos),
run every seedbank command from that repo: `cd <repo> && <bin> ...`.
1. Run `candidates`. For each candidate, decide from the evidence (the key,
its sources, `observe` history, a targeted read of the source if needed)
whether it is a stable "how this repo works" fact another session would
otherwise rediscover. Task status, one-off details and anything already
in `AGENTS.md` are not.
2. Promote each keeper with one short, imperative `--representation`
(a command, path or rule; under ~30 words). Correctness or safety
invariants get `--critical`. Default to `--tier warm --scope <topic>`;
use `hot` only for facts nearly every task needs.
3. On a contradiction refusal, read both facts and choose `--replace <id>`
when the new one is right; never `--force` two contradicting facts.
4. Run `compile`. Never edit `AGENTS.md` by hand.
Return:
```
Promoted: <fact id> <tier> <text> (one line each, or "none")
Skipped: <key> -- <reason> (one line each)
```
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |