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 agents/zyqzyq/unfour/docs_auditgit clone --depth 1 https://github.com/zyqzyq/UnfourWrote 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/agents/zyqzyq/unfour/docs_audit)<a href="https://agentmods.dev/agents/zyqzyq/unfour/docs_audit"><img src="https://agentmods.dev/badge/agents/zyqzyq/unfour/docs_audit.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 | $0.00000 | $0.01718 |
| Opus 5 | $0.00000 | $0.00859 |
| Sonnet 5 | $0.00000 | $0.00344 |
| Haiku 4.5 | $0.00000 | $0.00172 |
Grade A, and why
DOCS_AUDIT 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 3d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docs Audit
This audit records documentation ownership, stale references, and known conflicts after the package-context cleanup. It is a routing aid, not a second package progress tracker.
Current Source of Truth
| Area | Source of Truth | Notes |
|---|---|---|
| Global long-term agent rules | AGENTS.md |
Package boundaries, command-bus expectations, dependency discipline, and reporting requirements. |
| AI/Codex reading strategy | docs/agents/START_HERE.md |
Defines scoped reading order and legacy fallback behavior. |
| Current package and crate status | docs/project/PACKAGE_STATUS.md |
Authoritative for current package/crate status; supersedes status details in historical checkpoint docs. |
| Frontend package boundaries | packages/*/AGENTS.md and packages/*/README.md |
Local long-term rules and quick package orientation. |
| Command bus boundary | crates/unfour-command-bus/AGENTS.md, crates/unfour-command-bus/README.md, docs/engineering/command-bus.md |
Command bus is a Rust crate, not a frontend package. |
| Architecture explanation | docs/architecture/* |
Reference docs only; should not override docs/project/PACKAGE_STATUS.md. |
Legacy or Possibly Stale Docs
| File | Issue | Suggested Action |
|---|---|---|
docs/agents/PROJECT_MAP.md |
Historical structural snapshot; previously contained old package names and stale crate status. | Keep as architecture/reference map with a top-level status-source notice. |
docs/agents/PROJECT_STATE.md |
Checkpoint-style state with dated counts, verification totals, and release status. | Treat as legacy checkpoint context unless explicitly refreshed. |
docs/agents/NEXT_STEPS.md |
Dated next-step queue; can duplicate current status and open issues. | Use only when docs/project/NEXT_STEPS.md is absent and the task needs legacy checkpoint context. |
docs/agents/OPEN_ISSUES.md |
Dated issue list; can duplicate PACKAGE_STATUS.md risks. |
Use only as legacy issue context; do not let it override package status. |
docs/engineering/architecture.md |
Contains older Database/SSH "reserved" status language. | Mark as engineering history or update in a separate architecture refresh. |
docs/engineering/progress.md |
Maintains historical progress separate from PACKAGE_STATUS.md. |
Consider archiving or marking historical in a later pass. |
docs/engineering/task-breakdown.md |
Contains old PostgreSQL/MySQL task status. | Treat as historical planning unless refreshed. |
docs/user/USER_GUIDE.md |
Some user-facing capability notes still describe PostgreSQL/MySQL and secret storage as future/reserved. | Review separately before publishing user docs. |
docs/superpowers/* |
Plans/specs preserve historical task intent and may mention created files or old work phases. | Keep as historical artifacts; do not use as current package status. |
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.
- 3d ago First seen · 72 lines · 0 tokens per session scan A 4a394dbeb5ad
DOCS_AUDIT is an agent published in the GitHub repository zyqzyq/Unfour (2 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,718 tokens. 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 2026-08-31.
Other agents, from other repositories
altai-implementer
Implements one bounded ALTAI roadmap slice and its tests. Default working agent for roadmap PRs.
altai-explorer
Read-only ALTAI repository exploration. Use when file ownership or existing patterns are unclear before implementing a roadmap item.
altai-reviewer
Read-only diff review for a risky ALTAI PR. Reports actionable findings only.
altai-test-triage
Triages failing tests/logs into product defects, flaky tests, environment problems, and pre-existing failures.
Test Engineer
Writes tests first, then implementation. Strict TDD.
researcher
Sample subagent that does focused research on a single question.