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/thomas97460/quota-tracker/agents-mdgit clone --depth 1 https://github.com/Thomas97460/quota-trackerWrote 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/thomas97460/quota-tracker/agents-md)<a href="https://agentmods.dev/instructions/thomas97460/quota-tracker/agents-md"><img src="https://agentmods.dev/badge/instructions/thomas97460/quota-tracker/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 | $0.02472 | $0.02472 |
| Opus 5 | $0.01236 | $0.01236 |
| Sonnet 5 | $0.00494 | $0.00494 |
| Haiku 4.5 | $0.00247 | $0.00247 |
Grade A, and why
quota-tracker 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 5d 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guidelines — quota-tracker
Commits
Never add Co-Authored-By or any authorship trailer to commit messages.
Hard stops
- Never push a
vX.Y.Ztag without explicit human opt-in in the current conversation. There is no release automation in this repo: pushing the tag is the act of promoting that commit to production, full stop — see "Release & promotion" below. - Never merge a PR touching a path listed in
.github/CODEOWNERS(.github/,nix/,flake.nix,SECURITY.md,AGENTS.md,CLAUDE.md) without the human explicitly saying so in the conversation — even though auto-merge intomainis otherwise permitted. GitHub can't enforce this by itself here: the agent acts under the same GitHub identity as the human (see "Workflow" below), and GitHub blocks an account from approving its own PR, so a code-owner-review requirement would just permanently block every agent-opened PR. This is a procedural rule, not an ACL — seeCONTRIBUTING.mdfor how this was resolved. - Never move or delete an existing
v*tag — the tag ruleset blocks this for everyone except the repository admin role, and even then it should never happen (see "Rollback": always roll forward with a new tag). - No secrets in versioned files.
- Unit test coverage ≥ 90% (
pytest --cov-fail-under=90) and docstring coverage ≥ 90% (interrogate) are enforced by required CI checks; do not lower, bypass, or remove either gate. mypyruns instrictmode; do not relax it.- Do not add quality-gate bypasses such as
# pragma: no cover,# type: ignore,# noqa, or equivalent ruff/mypy/pytest exclusions unless a real constraint makes it unavoidable. Any exception must be narrow and documented next to the suppression. - Never edit
.github/rulesets/*.jsonor runscripts/github/apply-governance.shwithout explicit human go-ahead — it mutates live GitHub branch/tag protection on the real repo. quota_tracker/providers/andquota_tracker/db/must never import fromquota_tracker/api/orquota_tracker/daemon.py(see "Code rules").
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.
- 5d ago First seen · 183 lines · 2,472 tokens per session scan A 5d45e09149c6
quota-tracker AGENTS.md is an instructions file published in the GitHub repository Thomas97460/quota-tracker (15 stars, last pushed 3d ago), licensed MIT. It adds 2,472 tokens to every session, about $0.0124 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
DPlex copilot-instructions.md
Copilot instructions for Ron537/DPlex, covering dplex — copilot instructions, build & run, architecture, process boundaries and provider system (ai tool abstraction).
Project-AMBER AGENTS.md
AGENTS.md instructions for JJHbrams/Project-AMBER, covering agent orchestration, roles and non-negotiable rules.
Project-AMBER project-guides.instructions.md
Project coding guidelines, todo monitoring rules, and context for AI agents working on Project Engram.
ai-workflow AGENTS.md
Instructions for cunhaax/ai-workflow, covering ai workflow template, rules — non-negotiable, project overview, commands and architecture.
trackly-cli CLAUDE.md
Claude Code instructions for trackly-app/trackly-cli, covering trackly-cli, tech stack, backend production source of truth, directory structure and key commands.
vibetags com-example-config-AsyncTestConfig.instructions.md
Instructions for PIsberg/vibetags, covering copilot instructions for asynctestconfig and immutable type.