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/dinpd/agentaction/agents-mdgit clone --depth 1 https://github.com/dinpd/AgentActionWhat 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 | $0.00310 | $0.00310 |
| Opus 5 | $0.00155 | $0.00155 |
| Sonnet 5 | $0.00062 | $0.00062 |
| Haiku 4.5 | $0.00031 | $0.00031 |
Grade A, and why
AgentAction 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.
What it actually says
AgentAction Delivery Instructions
Follow the issue-to-merge workflow for every software change in this
repository. Preserve unrelated local changes and do not report completion until
the remote default branch contains the verified change.
Release responsibility
Classify the release impact before implementing each change and record it in the issue and pull request.
A change is significant functionality when it adds or materially changes a
user-visible capability, public API, CLI behavior, schema, package export,
authorization or evidence behavior, hosted gateway contract, or required
migration. Significant functionality must execute the release process in
docs/releasing.md in the same delivery task unless the
user explicitly narrows the task to an earlier gate. Do not wait for the user
to remember or separately request the release.
Use a minor release for significant functionality while the project is below
1.0, a patch release for backward-compatible fixes, and a prerelease when the
release policy identifies elevated compatibility or operational risk. Pure
documentation, test-only, internal refactoring, and unreleased experimental
changes may be marked no release, with a brief rationale.
For a release-bearing task:
- update version metadata and
CHANGELOG.mdin the pull request; - run the release gates documented in
docs/releasing.md; - merge through the normal issue-to-merge process;
- create and push the matching version tag;
- verify that the release workflow publishes the GitHub release and artifacts.
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 · 34 lines · 310 tokens per session scan A 88731a798d1a
AgentAction AGENTS.md is an instructions file published in the GitHub repository dinpd/AgentAction (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 310 tokens to every session, about $0.0015 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
Synapsor-Runner AGENTS.md
Instructions for Synapsor/Synapsor-Runner, covering agent guide for synapsor runner, first commands, what not to change casually, how the flow works and add a capability without reading dist/.
mcp-sentinel CLAUDE.md
Claude Code instructions for kirandevihosur74/mcp-sentinel, covering claude.md, what this is, rules, bright data scraper configuration and registries.
Synapsor-Runner copilot-instructions.md
Instructions for Synapsor/Synapsor-Runner, a project described as: Let AI agents query and update Postgres/MySQL without raw SQL, unrestricted schema access, or database credentials in the model; writes stay reviewed.
Synapsor-Runner CLAUDE.md
Instructions for Synapsor/Synapsor-Runner: Use AGENTS.md as the source of truth for this repo.
kasa-mcp AGENTS.md
AGENTS.md instructions for aikadimsoy/kasa-mcp, covering kasa — çalışma kuralları / working rules, ölçüm disiplini (asıl ip — atlanmaz), sessiz arıza — bu projenin baş düşmanı, tehdit modeli — aktör etiketi (zorunlu) and bilinen ortam tuzakları.
kasa-mcp CLAUDE.md
Claude Code instructions for aikadimsoy/kasa-mcp, covering kasa — çalışma kuralları / working rules, ölçüm disiplini (asıl ip — atlanmaz), sessiz arıza — bu projenin baş düşmanı, tehdit modeli — aktör etiketi (zorunlu) and bilinen ortam tuzakları.