Borrowing it
Nothing to install: this file belongs to olddonkey/olddonkey-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/olddonkey/olddonkey-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/olddonkey/olddonkey-skillsWrote 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/olddonkey/olddonkey-skills/agents-md)<a href="https://agentmods.dev/instructions/olddonkey/olddonkey-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/olddonkey/olddonkey-skills/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/olddonkey/olddonkey-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/olddonkey/olddonkey-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.02287 | $0.02287 |
| Opus 5.5 | $0.00915 | $0.00915 |
| Sonnet 5.5 | $0.00457 | $0.00457 |
| Haiku 4.5 | $0.00229 | $0.00229 |
Grade C, and why
olddonkey-skills AGENTS.md scanned grade C with 2 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 12d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
installer for the Cursor plugin (`curl … install-cursor.sh | bash`), plus its Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
installer for the Cursor plugin (`curl … install-cursor.sh | bash`), plus its How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
What this repo is
A collection of Agent Skills (Markdown SOPs + helper Bash scripts) published
as both a Claude Code marketplace (.claude-plugin/marketplace.json) and a
Cursor marketplace (.cursor-plugin/marketplace.json). It is not a deployable
service. There are no repo-level dependency manifests (no package.json,
lockfile, or Makefile at the root); the toolchain — bash, git, Node.js/npm,
and python3 3.11+ (tomllib) — is expected to be preinstalled, so a startup
update script has nothing to install.
Components:
skills/implementation-loop/— the implementation loop skill: one model implements, a model from another vendor reviews, and the session owns the gate and publication. The two backend modules live underbackends/{claude,codex}/, each withdispatch.sh,runtime.md,selftest.sh, andfixture-driver.sh.backends/backends.tsvregisters their capabilities. The grok and cursor-agent backends were removed in 2026-10 and stay in main's history. Shared suites and the opt-in real-backend gate live undertests/; the frozen Codex matrix istests/codex-cases.tsv.scripts/run-gate.shremains the backend-neutral gate, whilescripts/codex-dispatch.shandscripts/selftest.share one-release forwarding shims removed in 0.5.0. The shared observable interface is recorded inreferences/dispatch-contract.mdand enforced by the contract suites. The headlessloop-coordinator(collab-canvas) was removed in 2026-10 becauseSKILL.mdnever called it; it stays in main's history and on thecanvas-u3-runbranch. The journal, index, console, calibration store, evidence card, andloop-runwere removed at the same time; dial records live in user-level private memory (authorizations) and the repo's CLAUDE.md (repo facts), asSKILL.mddescribes.skills/engineering-mode/— goal-first wrapper over the loop. Shared playbooks inreferences/playbooks/, plusscripts/tree-oid.shand its selftest.skills/web-slides/— a scaffolder (scripts/scaffold.sh) that generates a runnable Vite + React + TypeScript slide deck. The only runnable "app".cursor-implementation-loop/— the generated Cursor plugin port. It ships two skills (cursor-implementation-loop,cursor-engineering-mode) and two agents (agents/loop-implementer.md,agents/loop-independent-reviewer.md). Edit shared inputs underskills/or Cursor-authored inputs underhosts/cursor/, then runbash build.sh; do not hand-edit the generated tree. Manifest:.cursor-plugin/plugin.json.build.sh,hosts/cursor/,tests/build-{inventory.py,selftest.sh}— the deterministic Cursor-package generator, its host-only overlay, and its external-inventory/selftest tooling.bash build.sh --checkverifies the committed tree and its recorded version decision without rewriting it.install-cursor.sh/install-cursor-selftest.sh— root-level one-line installer for the Cursor plugin (curl … install-cursor.sh | bash), plus its own selftest.plans/,docs/— design plans and review records; prose only, no CI hooks.
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.
- 12d ago Changed · -12 lines · -156 tokens per session 77c91f564787
- 13d ago Changed · -159 lines · -3,046 tokens per session 9b7504f0ca10
- 21d ago Changed · +168 lines · +3,047 tokens per session e4a882511fb8
- 23d ago Changed · +6 lines · +105 tokens per session 127557852dff
- 24d ago Changed · +7 lines · +138 tokens per session cf52ff98fe07
- 27d ago Changed · +23 lines · +386 tokens per session 196070c56acd
- 1mo ago First seen · 126 lines · 1,813 tokens per session scan C 5e791164cfeb
olddonkey-skills AGENTS.md is an instructions file published in the GitHub repository olddonkey/olddonkey-skills (17 stars, last pushed 13d ago), licensed MIT. It adds 2,287 tokens to every session, about $0.0091 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.