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/cirwel/unitares/agents-mdgit clone --depth 1 https://github.com/cirwel/unitaresWrote 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/cirwel/unitares/agents-md)<a href="https://agentmods.dev/instructions/cirwel/unitares/agents-md"><img src="https://agentmods.dev/badge/instructions/cirwel/unitares/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 | $0.06399 | $0.06399 |
| Opus 5 | $0.03200 | $0.03200 |
| Sonnet 5 | $0.01280 | $0.01280 |
| Haiku 4.5 | $0.00640 | $0.00640 |
Grade A, and why
unitares AGENTS.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 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 — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — unitares
Bootstrap for Codex (and other non-Claude) sessions in this repo. This file is the machine-facing Codex bootstrap. Content below the SHARED CONTRACT markers is kept byte-identical with CLAUDE.md — CI (scripts/dev/check-shared-contract.sh) enforces parity. Edit shared rules in both files; edit the Codex preamble here only.
For the human-facing Codex quickstart, see CODEX_START.md.
The installable Codex/Claude adapter bundle is canonical in the companion unitares-governance-plugin repo. This file only governs how Codex should behave while working directly inside the unitares server repo.
Codex-specific wiring
Codex exposes synchronous lifecycle hooks, but they do not imply a continuously
running agent. The expected state-writing profile is sparse: the agent usually
makes zero or one meaningful sync_state call during a turn, and the plugin's
Stop hook may add one automatic substrate_interpretation after the turn. Only
the former is an agent-authored check-in. Lazy onboarding can also write a
synthetic bootstrap row; initialization is not a real check-in. PostToolUse
receipts and optional hook-parent heartbeats are audit evidence only — never
agent runtime, progress, or EISV. Do not manufacture per-tool or per-edit
check-ins.
Slash commands (commands/*.md)
/governance-start— onboard or resume; refreshes local continuity state/checkin— governance update for the current turn, plus meaningful milestones/diagnose— identity, state, and operator diagnostics/dialectic— structured review/closeout— final workspace hygiene check; reports dirty files, Git delivery state (local vs pushed/merged), and repo-rooted processes; can stash/stop when cleanup is requested
Raw tool flow when slash commands are unavailable: start_session(force_new=true, parent_agent_id=<prior uuid if continuing>, spawn_reason="new_session") → save agent_uuid + client_session_id → sync_state(response_text, complexity, client_session_id=...) only when there is meaningful agent state to report (typically at most once per assistant turn) → check_working_state() for read-only checks → health_check() only if system health is suspect. Canonical/raw equivalents are onboard(...), process_agent_update(...), and get_governance_metrics(...).
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 · 347 lines · 6,399 tokens per session scan A c14466b036ef
unitares AGENTS.md is an instructions file published in the GitHub repository cirwel/unitares (4 stars, last pushed 3d ago), licensed Apache-2.0. It adds 6,399 tokens to every session, about $0.0320 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 2026-08-31.
Other instructions, from other repositories
fluent AGENTS.md
AGENTS.md instructions for mrinalwadhwa/fluent, covering instructions for coding agents, fluent workflow, commit messages, subject line and body.
eigenflux AGENTS.md
AGENTS.md instructions for phronesis-io/eigenflux, covering agents.md - eigenflux server development guidelines, project overview, development environment, directory responsibilities and module documentation (docs/dev/).
FrameCode-VibeWork AGENTS.md
Instructions for Sistema2D/FrameCode-VibeWork, covering agents.md, instruction order, reading-trigger rule, regression rule and when a plan is required.
pocketpaw AGENTS.md
AGENTS.md instructions for pocketpaw/pocketpaw, covering agents.md, agent identity, supported backends, capabilities and file system.
rebar AGENTS.md
Instructions for willackerly/rebar, covering agents.md — working on rebar itself, read before coding, core tenets, agent autonomy and session lifecycle.
coordinate-agents AGENTS.md
AGENTS.md instructions for hogancv/coordinate-agents, covering repository instructions for ai contributors, canonical identity, repository map, required checks and change rules.