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/lidless-labs/immichctrl/agents-mdgit clone --depth 1 https://github.com/lidless-labs/immichctrlWhat 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 | $0.01086 | $0.01086 |
| Opus 5 | $0.00543 | $0.00543 |
| Sonnet 5 | $0.00217 | $0.00217 |
| Haiku 4.5 | $0.00109 | $0.00109 |
Grade A, and why
immichctrl 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 2d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - Working In This Repo
This repo is Brigade-wired. These are the operating rules for any agent working here.
Every Session
For substantial work, first gather context:
- Read this file - operating rules and the memory handoff contract.
- Read the repo's
READMEandCONTRIBUTING(if present) for build, test, and style expectations. - Skim your harness's handoff inbox (
.claude/memory-handoffs/) for recent notes from other sessions. - Read
SAFETY_RULES.mdonce. Hard boundaries.
For tiny read-only commands, do the command directly and avoid loading unrelated context. Do not ask permission for normal context gathering.
Definition of Done
Before you report work as complete:
- Run the project's checks (tests, linters, type checks, build). If you do not know them, look in
README,CONTRIBUTING,pyproject.toml/package.json, or the CI config before guessing. - Report the actual result. Never claim success you did not observe; paste the command you ran and its output.
- If a check could not run, say so and name the blocker instead of guessing.
- If the session produced durable knowledge, confirm a Memory Handoff was written (see below).
Memory Owner
The configured memory owner is claude. Side harnesses may keep local session context, but durable knowledge must be written as a Memory Handoff in your harness's own inbox (.claude/memory-handoffs/). The memory owner ingests those handoffs into canonical durable memory; reviewed repo-local notes land under .learnings/.
If you are not the memory owner, do not edit SAFETY_RULES.md, rules/, or .learnings/ as canonical memory unless the user explicitly asks for that file edit. Do not create a second canonical memory system.
Memory Handoff (Mandatory)
If a session discovers durable knowledge - architecture decisions, workflow changes, non-obvious fixes, setup gotchas, security findings, reusable commands, durable research, or user preferences - create a handoff at the end of the task.
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.
- 2d ago First seen · 77 lines · 1,086 tokens per session scan A 0f23a2bd6467
immichctrl AGENTS.md is an instructions file published in the GitHub repository lidless-labs/immichctrl (5 stars, last pushed 1mo ago), licensed MIT. It adds 1,086 tokens to every session, about $0.0054 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
moira AGENTS.md
Instructions for moira-mcp/moira, covering agents.md, what moira is, repository layout, build & run (fresh clone) and image: line and uncomment the build: block, then.
ARR_MCP AGENTS.md
Instructions for GauranshMathur/ARR_MCP, covering agents.md, non-negotiables, researching a service, adding a service and tool design.
ARR_MCP CLAUDE.md
Instructions for GauranshMathur/ARR_MCP, covering claude.md, build and run commands, code style guidelines, agent skills and issue tracker.
mcpelevator CLAUDE.md
Instructions for pacnpal/mcpelevator, covering commands, architecture, conventions, agent skills and issue tracker.
mcpelevator AGENTS.md
Instructions for pacnpal/mcpelevator, covering commands, architecture and conventions.
munin-memory AGENTS.md
AGENTS.md instructions for Magnus-Gille/munin-memory, covering munin memory — project instructions, instruction contract, project purpose and architecture, sources of truth and session and state discipline.