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/ychamel/reporesident/claude-mdgit clone --depth 1 https://github.com/ychamel/RepoResidentWrote 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/ychamel/reporesident/claude-md)<a href="https://agentmods.dev/instructions/ychamel/reporesident/claude-md"><img src="https://agentmods.dev/badge/instructions/ychamel/reporesident/claude-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 | $0.01623 | $0.01623 |
| Opus 5 | $0.00812 | $0.00812 |
| Sonnet 5 | $0.00325 | $0.00325 |
| Haiku 4.5 | $0.00162 | $0.00162 |
Grade C, and why
RepoResident CLAUDE.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 4d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
## Delegation <!-- only if your tool can spawn subagents; otherwise ignore this section --> How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Operating Manual
You operate this repo through the harness in .agent/ — persistent state and procedures that let
any session, on any model, pick up work with minimal context and leave the repo better than found.
First session on this repo? .agent/STATE.md will route you to bootstrap.
Prime directives
- The user outranks this file; this file outranks habit. When rules conflict: Hard rules > active workflow > style sections.
- Correct and complete beats fast. No stubs, no placeholder code, no mock data outside tests, no silently narrowed scope. If you can't finish honestly, say exactly what's missing.
- Smallest sufficient context:
.agent/MAP.md→ area doc if one exists → grep → read only implicated files. Never read directories wholesale. Lost after ~3 file reads? Re-scope from MAP or the area doc instead of reading more code. - Never call an API/function you haven't seen defined this session — read its definition first. Unsure how something behaves? Verify in source, not from memory.
- Code is truth; docs serve code. A wrong harness doc is a bug — fix it in passing (≤5 lines)
or leave a
flag:in the journal. - Chat carries outcomes; files carry detail. Long analysis →
.agent/scratch/, designs →.agent/designs/, lasting choices →.agent/DECISIONS.md, deferred bugs/work →.agent/ISSUES.md.
Session protocol
START: read .agent/STATE.md → classify the request (routing below) → open that one workflow
file and follow it. Read only what the workflow tells you to read.
DURING: after each completed slice/checkpoint, update the Active: line in STATE.md (crash insurance).
END — mandatory whenever you changed anything:
- Rewrite
.agent/STATE.mdin full (template is inside it; Session +1). - Append to
.agent/journal/<YYYY-MM>.md:S<n> <YYYY-MM-DD> <workflow>: outcome + key files(≤4 lines; optionallyflag: <debt/risk noticed>). - Structure changed → update MAP.md. Lasting choice made → one line in DECISIONS.md.
- Tick your workflow's Done checklist in your final message.
If the new Session number is a multiple of 10, add "maintenance due" to STATE
Next:(run.agent/workflows/maintain.mdnow if the session has room).
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.
- 4d ago First seen · 105 lines · 1,623 tokens per session scan C bc4554f1c2f3
RepoResident CLAUDE.md is an instructions file published in the GitHub repository ychamel/RepoResident (6 stars, last pushed 6d ago), licensed MIT. It adds 1,623 tokens to every session, about $0.0081 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
cctop AGENTS.md
AGENTS.md instructions for st0012/cctop, covering agents.md - development guide for cctop, scope and sources, required development rules, driver workflow and github and pr rules.
pixir AGENTS.md
Instructions for Ranvier-Technologies/pixir, covering agents.md - pixir harness, progressive discovery, screaming architecture, beta stance and commands.
pixir CLAUDE.md
Instructions for Ranvier-Technologies/pixir, covering pixir harness - legacy agent guide, current map and commands.
plastic AGENTS.md
AGENTS.md instructions for zalom/plastic, covering plastic, stack, defaults, searching plastic with qmd and working on plastic.
slipway AGENTS.md
AGENTS.md instructions for signalridge/slipway, covering slipway agent principles, user owns the process, investigate before clarifying, report, do not certify and maintain the whole surface.
ai-harness CLAUDE.md
Claude Code instructions for samartomar/ai-harness, covering ai-harness — claude bootloader, vocabulary — two different things, read the source, not a summary of it, start here and self-hosting boundary.