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/zhu-kai/whodecided/agents-mdgit clone --depth 1 https://github.com/zhu-kai/whodecidedWrote 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/zhu-kai/whodecided/agents-md)<a href="https://agentmods.dev/instructions/zhu-kai/whodecided/agents-md"><img src="https://agentmods.dev/badge/instructions/zhu-kai/whodecided/agents-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 | $0.01331 | $0.01331 |
| Opus 5 | $0.00665 | $0.00665 |
| Sonnet 5 | $0.00266 | $0.00266 |
| Haiku 4.5 | $0.00133 | $0.00133 |
Grade C, and why
whodecided AGENTS.md scanned grade C 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 5d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **Data sovereignty.** Truth is plain text in `.wdd/`. `rm -rf` the tool and everything stays readable with cat/jq/grep. How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI agents and contributors working on whodecided itself.
What this is
A thin TypeScript CLI that distills the decisions an AI coding agent (and you) made inside Claude Code / Codex sessions into an append-only, ratifiable ledger, then feeds ratified precedent back to agents. "Common law for agentic coding."
The product is: a schema + a discardable CLI + a .wdd/ directory of plain text inside the user's repo. git, claude -p/codex exec, and the browser are shelled out. The tool holds no state of its own.
Build / test / run
npm run build # tsc → dist/
npm test # vitest (unit tests live next to sources as *.test.ts)
node dist/cli.js --help
- Node ≥ 20, ESM (
"type": "module"→ import paths use.js). - Single runtime dependency:
yaml. Do not add more; argv parsing and everything else is stdlib. dist/andplanning/are gitignored. Design docs (SPEC.md, REVIEW-SPEC.md, CROSS-REVIEW.md) live inplanning/— read them for the full rationale; they are not published.
Architecture
Read-only pipeline with exactly two write points (distill → ledger, ratify → ledger):
cli.ts → commands/* command routing + orchestration
transcript/ locate + parse CC (~/.claude/projects) and Codex (~/.codex/sessions rollouts) → SessionEvent[]
extract/ candidates deterministic decision candidates + aware heuristics (NO LLM)
distill/ detect + distiller auto-detect claude/codex (config wins, sessions vote) → subprocess → LedgerEntry[] (schema-validated, retry, degrade)
ledger/ schema + io append-only jsonl read/write; verdictOf/isPinned/noteOf
patch/ apply THE single write path: validate → append ratify lines → (opt) commit
ledger/ evidence persisted (redacted) transcript excerpt per decision, keyed by ref
extract/ redact mask secrets before a slice reaches the distiller or evidence
checks/ gate diff-signals risk supersede coverage pure triage signals over ledger/diff/traces
commands/ signals assembles branch diff + per-decision signals for review/board/report
render/ term/md/html terminal docket / PR markdown / single-file workbench (Timeline + Threads tabs, keyboard review, change map, per-decision diff, triage)
config.ts git.ts jsonl.ts validate.ts infra (git.ts: branchDiff/churn/productFiles)
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.
- 5d ago First seen · 64 lines · 1,331 tokens per session scan C a18ae20ff94c
whodecided AGENTS.md is an instructions file published in the GitHub repository zhu-kai/whodecided (22 stars, last pushed 1mo ago), licensed MIT. It adds 1,331 tokens to every session, about $0.0067 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
EverOS CLAUDE.md
Claude Code instructions for EverMind-AI/EverOS, covering everos — md-first memory extraction framework, quick commands, architecture, engineering practices and branch strategy.
remnic AGENTS.md
AGENTS.md instructions for joshuaswarren/remnic, covering remnic - agent guide, architecture boundaries (non-negotiable), upstream references, adapter implementation rules and openclaw compatibility window.
plur CLAUDE.md
Claude Code instructions for plur-ai/plur, covering claude.md, what is plur, development, package dependency and version bumps.
honcho CLAUDE.md
Claude Code instructions for plastic-labs/honcho, covering claude.md, honcho overview, what is honcho?, core concepts and peer paradigm.
braindb CLAUDE.md
Claude Code instructions for dimknaf/braindb, covering braindb — claude instructions, ⚠ tool priority — read this first, it overrides habit, at the start of every session, 1. get always-on rules (behavioral guidelines) and project structure.
pi-extensions CLAUDE.md
Claude Code instructions for MattDevy/pi-extensions, covering claude.md, commands, architecture, data flow and key modules.