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/akash97p/agent-notify/agents-mdgit clone --depth 1 https://github.com/Akash97p/agent-notifyWhat 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 | $0.00738 | $0.00738 |
| Opus 5 | $0.00369 | $0.00369 |
| Sonnet 5 | $0.00148 | $0.00148 |
| Haiku 4.5 | $0.00074 | $0.00074 |
Grade A, and why
agent-notify 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentNotify agent workflow
These instructions apply to every coding agent working in this repository.
Start or resume work
- Read
docs/DEVELOPMENT_STATE.md,docs/FEATURE_BACKLOG.md,TODO.md, and the relevant architecture/security documentation. - Inspect
git status, the current branch, and recent commits before editing. - Preserve user changes and runtime secrets. Never read or print the bearer token unless direct API debugging was explicitly requested.
- Update
docs/DEVELOPMENT_STATE.mdwhenever a decision, verification result, migration, or next step would otherwise be lost after context compaction.
Local Git workflow
- This repository is local-only unless the user explicitly asks to configure or use a remote.
mainis the stable release line. Never edit or commit while checked out onmain.devis the integration branch. Do not implement features directly ondev.- Create each branch from an up-to-date local
dev:feature/<short-name>for product capabilities;fix/<short-name>for defects;docs/<short-name>for documentation;test/<short-name>for test-only work;chore/<short-name>for tooling and maintenance.
- Keep commits focused and use imperative Conventional Commit subjects such as
feat: add webhook delivery. - Build and test the branch in proportion to its risk. Update documentation and migrations in the same branch as the behavior they describe.
- Merge a verified branch into local
devwithgit merge --no-ff. Delete the local topic branch after the merge when safe. - Start the next topic branch from the newly merged
dev. - Never rewrite shared history, force-push, or use destructive Git commands.
Required quality gates
Run Windows .NET tooling through the repository scripts from WSL:
./scripts/build.sh
./scripts/test.sh
./scripts/package.sh
For narrow iterations, targeted tests are acceptable during development; the full build and test suite are required before merging to dev. Packaging is required when installer payload, embedded resources, publish settings, or release automation changes.
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 · 65 lines · 738 tokens per session scan A bd72f2af10ef
agent-notify AGENTS.md is an instructions file published in the GitHub repository Akash97p/agent-notify (1 stars, last pushed 2d ago), licensed MIT. It adds 738 tokens to every session, about $0.0037 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
thinkrail AGENTS.md
Instructions for JetBrains/thinkrail, covering thinkrail, module structure & boundaries (top-priority requirement), engine: pi only, in-process, architecture (three rings) and repo layout.
snip CLAUDE.md
Instructions for edouard-claude/snip, covering claude.md, project overview, key concept, repository structure and architecture.
toktrack CLAUDE.md
Instructions for mag123c/toktrack, covering toktrack, quick start, context, workflow and 코드 구현 작업.
AmbyKit AGENTS.md
Instructions for ambystechcom/AmbyKit, covering agents.md — ambykit, what ambykit is, golden rules, project structure and build & test.
coograph brutal-honesty.instructions.md
Global communication style — applies to all workspaces and conversations.
coograph testing.instructions.md
Conventions for test files — loaded only when editing tests.