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/kirodotdev/kirocrew/agents-mdgit clone --depth 1 https://github.com/kirodotdev/KiroCrewWhat 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 | $0.08981 | $0.08981 |
| Opus 5 | $0.04491 | $0.04491 |
| Sonnet 5 | $0.01796 | $0.01796 |
| Haiku 4.5 | $0.00898 | $0.00898 |
Grade A, and why
KiroCrew 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 today.
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 — 500 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rules for AI Assistants
This file is a ROUTER, not a manual. It carries only the rules whose violation
causes damage before a pointer could be read. Everything else is a link you MUST
open before touching that subsystem: see
Read before you touch. The frontend has its own router,
website/AGENTS.md.
What this is
Kiro Crew is an open-source personal AI agent: chat from the web dashboard, the
CLI, or a messaging channel like Slack and Discord; run multi-step tasks
unattended; schedule cron jobs; keep memory across
sessions. It drives an LLM through the KiroACP provider (the ACP adapter running
kiro-cli over ACP JSON-RPC) plus MCP tools.
- Backend: Python package
kiro_crewinsrc/kiro_crew/. - Frontend: React + TS + Vite SPA in
website/; the builtdist/is staged intosrc/kiro_crew/static/dist/and served by the backend. - Data home:
~/.kiro/crew, overridden withKIROCREW_HOME. The legacy~/.kirocrewis fully deprecated and no longer auto-migrates; it survives only in sensitive-path deny lists, which must keep covering it. - Distribution: public GitHub, plain setuptools, public PyPI / public npm.
Full map: docs/architecture/overview.md.
Read before you touch
Load the doc for the row you are working in before you change code. Update it in the same commit when you change what it documents.
| If you are touching… | Read first |
|---|---|
platform/, editions, CPP seam, governance |
platform-context + governance |
security.py, hooks.py, denied commands, sensitive paths |
security + sel |
| the security model as a whole, threat boundaries | security-deep-dive |
computer_use/ |
computer-use |
acp/, kiro-cli transport, providers |
acp-client + providers |
| adding or adapting an agent harness (BYO, KAS, claude seam) | harness-parity (invariants) + harness-parity-gate (CI) |
| sessions, slots, session keys, PIDs | session + history |
| session summaries, the chat summary panel, intent extraction | session-summary |
| memory, embeddings, vectors, lessons, skills, hooks | memory-skills-hooks |
| MCP servers or tools (adding, changing, statelessness) | mcp |
| apps, App Kit, manifests, app agents | app-kit-platform + app-kit/ |
| artifacts, companion chat | artifacts |
stt/, transcribe.py, voice_reply.py, the mic, dictation, TTS |
stt-streaming + voice-streaming |
| cron, learn, dashboard handlers | learn-cron-dashboard |
| Slack, Discord, any channel, messaging, approvals | messaging + slack-gateway |
| subagents, spawn, orphan recovery | subagent |
| task runner | task + taskrunner |
workflows/ (the dynamic-workflow engine) |
workflows + workflow-gates |
| themes | themes + theming-contract |
anything under website/ |
website/AGENTS.md |
| user-facing strings, dates, numbers, sort order | i18n-catalog (authoring) + i18n-gates (CI) |
| tests: flakes, speed, fixtures, sharding, side effects, conftest isolation | testing-conventions + the writing-tests skill |
| browser E2E | e2e-gate |
| CI, PR flow, review gates | ci-and-reviews + CONTRIBUTING.md |
| constants, magic numbers, where a limit lives | code-style |
injected [Cron notification] / [Subagent completion event] |
injected-messages |
| build, install, dev mode | CONTRIBUTING.md + install |
| Windows / cross-platform process, signal, lock, metrics | windows-install + the shim table below |
a release, or CHANGELOG.md |
release |
| errors, retries, user-facing failure text | error-handling |
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.
- today Changed · +8 lines · +147 tokens per session b157385e39aa
- 2d ago First seen · 492 lines · 8,834 tokens per session scan A 7408e2eb6ec7
KiroCrew AGENTS.md is an instructions file published in the GitHub repository kirodotdev/KiroCrew (3,532 stars, last pushed today), licensed Apache-2.0. It adds 8,981 tokens to every session, about $0.0449 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
trueforge AGENTS.md
AGENTS.md instructions for truefoundry/trueforge, a project described as: The open-source agent harness - the runtime layer that turns an LLM into a working agent.
relay AGENTS.md
Instructions for AgentWorkforce/relay, covering git workflow rules, never push directly to main, correct workflow, ... do work .. and stop here - let user merge.
LeAgent AGENTS.md
Instructions for vixues/LeAgent, covering leagent development guidelines, project overview, architecture, execution topology (one kernel, many ingresses) and surface map (where things live).
grix AGENTS.md
Instructions for askie/grix, covering grix agent guide, repository boundaries, required workflows, shared agent configuration and cross-component contracts.
atlasclaw CLAUDE.md
Instructions for CloudChef/atlasclaw, covering openspec instructions, language preference and workflow.
rn-dev-agent AGENTS.md
Instructions for Lykhoyda/rn-dev-agent, covering repository guide for agents, repository map, editing rules, architecture rules and supported node runtimes.