Borrowing it
Nothing to install: this file belongs to TheStreamCode/agentic-rd-skill. 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/TheStreamCode/agentic-rd-skill/main/AGENTS.mdgit clone --depth 1 https://github.com/TheStreamCode/agentic-rd-skillWrote 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/thestreamcode/agentic-rd-skill/agents-md)<a href="https://agentmods.dev/instructions/thestreamcode/agentic-rd-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/thestreamcode/agentic-rd-skill/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/thestreamcode/agentic-rd-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/thestreamcode/agentic-rd-skill/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 | $0.01439 | $0.01439 |
| Opus 5.5 | $0.00576 | $0.00576 |
| Sonnet 5.5 | $0.00288 | $0.00288 |
| Haiku 4.5 | $0.00144 | $0.00144 |
Grade A, and why
agentic-rd-skill 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 2mo 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Instructions
These instructions apply to the entire repository. Preserve narrower instructions if a future subdirectory adds its own AGENTS.md.
Purpose And Sources Of Truth
This repository publishes a portable Agent Skill plus a dependency-free Node.js workflow CLI.
skills/agentic-rd-skill/is the installable package.skills/agentic-rd-skill/SKILL.mdis the concise activation and operating contract.skills/agentic-rd-skill/references/workflow.mdis the detailed workflow/state reference.skills/agentic-rd-skill/scripts/rd.mjsis the executable state-machine implementation.skills/agentic-rd-skill/assets/contains the canonical artifact templates.README.mddocuments public behavior and installation.evals/contains dated evidence. Historical snapshots must not be presented as current measurements.project-brief.mdandwork/are ignored local dogfood artifacts, not tracked product source.
When documentation and runtime behavior disagree, verify the CLI and tests, then update every affected source of truth in the same change.
Repository Invariants
- Support Node.js 20 or newer and keep the installable skill free of runtime dependencies.
- Keep portable frontmatter provider-neutral; never add host-specific
allowed-toolsor implicit external authority. - Preserve phase order: setup, evidence, plan, execution, results, cross-review, stage gate, final.
- New runs use workflow contract 1.1. Existing workflow 1.0 state remains readable; v0.3 workspaces are preserved and rejected rather than migrated.
- Setup remains
in_progressuntil the filled brief and run log pass their artifact contracts. - State-mutating commands validate the current global state and the candidate next state before writing. The documented stale-final recovery is the only scoped repair exception.
validatedistinguishes valid-incomplete, valid-complete, and invalid state. Structural validation is not semantic assurance.- Stage-gate approval requires at least 8/10, no zero dimension, and zero blockers.
- A requested revision must retain its ID and be resolved by an upstream artifact change or an explicit no-change disposition.
package.jsonis the single source of truth for the release version.SKILL.mdmetadata,CITATION.cff, the README version badge, and a datedCHANGELOG.mdrelease section must match it;npm run validatefails on any partial bump.- Do not hardcode the release version anywhere else. Scripts that need it must read it from
package.jsonor the shippedSKILL.mdfrontmatter. - The CLI is single-writer. Do not introduce concurrent state mutation without a designed locking/generation protocol and cross-platform tests.
- Preserve atomic state replacement, managed-path containment, symlink rejection, non-overwrite behavior, and explicit exit classes.
- Preflight the complete initialization layout before the first scaffold write; a late path conflict must leave earlier missing files untouched.
- Keep
currentPhaseequal to the latest non-pending phase and keep stage-gate score, dimensions, blockers, and decision metadata consistent with the gate status. - Treat profile/option names as exact whitelist members rather than inherited object keys, and keep paid-tool, credentialed-system, and external-write state budgets fail-closed.
- Never convert skipped or zero-execution host checks into a pass.
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.
- 2mo ago First seen · 91 lines · 1,439 tokens per session scan A 41a50060a70c
agentic-rd-skill AGENTS.md is an instructions file published in the GitHub repository TheStreamCode/agentic-rd-skill (1 stars, last pushed 4d ago), licensed MIT. It adds 1,439 tokens to every session, about $0.0058 per session on Opus 5.5. 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
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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.