Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/agent-field/plandb/claude-mdgit clone --depth 1 https://github.com/Agent-Field/plandbWrote 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/instructions/agent-field/plandb/claude-md)<a href="https://agentmods.dev/instructions/agent-field/plandb/claude-md"><img src="https://agentmods.dev/badge/instructions/agent-field/plandb/claude-md.svg" alt="Measured on agentmods" 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 | $0.01173 | $0.01173 |
| Opus 5 | $0.00587 | $0.00587 |
| Sonnet 5 | $0.00235 | $0.00235 |
| Haiku 4.5 | $0.00117 | $0.00117 |
Grade A, and why
plandb CLAUDE.md 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PlanDB — Project Instructions
What This Is
PlanDB is "the issue tracker your AI agents are missing" — a task graph database (CLI + MCP + HTTP) that agents use to decompose work, parallelize, adapt mid-flight, and persist knowledge. Single Rust binary, SQLite-backed.
Development
cargo build # build
cargo test # unit tests (8 tests)
bash tests/functional_test.sh # functional tests (7 scenarios)
cargo clippy # lints
cargo fmt --check # formatting
Rust 1.75+ required. No external dependencies — SQLite is bundled via rusqlite.
Branch Rules
mainis protected: CI must pass, no force push, no branch deletion- All changes go through PRs (admin can bypass for hotfixes)
- Branch naming:
feat/,fix/,docs/,refactor/,ci/ - Delete branches after merge
Commit Conventions
feat: new user-facing capability
fix: bug fix
refactor: code change that doesn't add features or fix bugs
docs: documentation only
ci: CI/CD changes
test: adding or fixing tests
chore: maintenance (deps, config, cleanup)
These prefixes drive automatic PR labeling via release-drafter.
Release Flow
Releases are intentional, not automatic. Every push to main runs CI but does NOT create a release.
How it works
PR merges to main
→ ci.yml runs (build, test, functional tests)
→ release-drafter updates a DRAFT release on GitHub (accumulates changes)
Ready to ship:
→ git tag v0.X.Y -m "description"
→ git push origin v0.X.Y
→ release.yml triggers:
1. Runs full test suite
2. Builds cross-platform binaries (linux x86/arm, macOS x86/arm, windows)
3. Generates checksums
4. Publishes GitHub release with auto-generated notes from the draft
Version bumping
- Patch (v0.2.0 → v0.2.1): bug fixes, docs, refactors
- Minor (v0.2.x → v0.3.0): new features
- Major (v0.x → v1.0): breaking changes
The release-drafter auto-suggests the next version based on PR labels (feat: → minor, fix: → patch).
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.
- 4d ago First seen · 128 lines · 1,173 tokens per session scan A 27bb046ff24b
plandb CLAUDE.md is an instructions file published in the GitHub repository Agent-Field/plandb (101 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 1,173 tokens to every session, about $0.0059 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 2026-08-30.
Other instructions, from other repositories
pipelex AGENTS.md
Instructions for Pipelex/pipelex, covering pipelex coding rules, codex cloud commands, linting, keyword-only arguments check and cleaning derived files.
pipelex CLAUDE.md
Instructions for Pipelex/pipelex, covering pipelex coding rules, commands, linting, keyword-only arguments check and cleaning derived files.
NEEDLE AGENTS.md
AGENTS.md instructions for jedarden/NEEDLE, covering needle codex guide, project overview, working safely, rust compatibility and code conventions.
NEEDLE CLAUDE.md
Claude Code instructions for jedarden/NEEDLE, covering needle project conventions, msrv, module dependency graph, code style and testing.
agentrun CLAUDE.md
Instructions for dmora/agentrun, covering agentrun — claude code project guide, library-first mindset, design philosophy — root is language, backends are dialect, build & test commands and architecture.
rnix CLAUDE.md
Instructions for rnixai/rnix, covering claude.md, project overview, project context, build & development commands and run a single test.