sdlc-studio AGENTS.md

sdlc-studio AGENTS.md is an instructions file for Codex, OpenCode from DarrenBenson/sdlc-studio. It costs 3,662 tokens per session, scanned A, original, MIT.

Repository instructions for sdlc-studio, a software-development workflow that uses reviews, status checks, lessons, and version-control updates before work begins.

In plain words
What is it for?
Use them at the start of each session, after context resets, and before design or implementation decisions in the sdlc-studio repository.
Why use it?
They help agents recover the current project state and follow rules that address recurring failures, including skipped checks and outdated repository data.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/darrenbenson/sdlc-studio/agents-md
Clone the repo
git clone --depth 1 https://github.com/DarrenBenson/sdlc-studio

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for sdlc-studio AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/darrenbenson/sdlc-studio/agents-md.svg)](https://agentmods.dev/instructions/darrenbenson/sdlc-studio/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/darrenbenson/sdlc-studio/agents-md"><img src="https://agentmods.dev/badge/instructions/darrenbenson/sdlc-studio/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,662 This file is loaded in full into every session.
When invoked 3,662 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.03662 $0.03662
Opus 5 $0.01831 $0.01831
Sonnet 5 $0.00732 $0.00732
Haiku 4.5 $0.00366 $0.00366

Measured 4d ago against content hash 57043c81e17c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdlc-studio AGENTS.md scanned grade A with 1 finding 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 4d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| `reconcile --verify` | whichever of `pytest`, `jest`, `vitest`, `go`, `curl`, `jq`, `rg` your Verify lines invoke |
AGENTS.md · 252 lines

How it starts

The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for coding agents working on this repository. Claude Code reads this via the @AGENTS.md import in CLAUDE.md; Codex, Copilot, Cursor, Gemini and others read it directly.

This file is always loaded. Keep it short enough to be read, and put nothing here that a command already prints. The pre-commit hook names every guard it runs, the rule it enforces, the offending line and the fix, so this file does not restate them.

Start here, every session

Do these four before acting, including after a context reset or compaction. They take under a minute and each one has cost a real sprint when skipped.

  1. sdlc-studio/reviews/LATEST.md - what the last run landed and what it left owed.
  2. /sdlc-studio status - pipeline state and the next step.
  3. .claude/skills/sdlc-studio/lessons/_index.md - the cross-project lessons. Read them before any design decision, not after.
  4. git fetch - a stale clone mints ids the remote already used and plans over artefacts somebody else changed.

The failure mode this repo actually has

Not ignorance. Rules that were read and then not followed. One session produced five instances: the lessons index went unread while the plan printed its digest; review prompts were hand-written though the shipped seat briefs exist; findings were not sorted into regression versus pre-existing; a backlog census was hand-scripted rather than taken from the tooling; and the full-suite-before-commit rule was broken one commit after being shipped, leaving main red for six commits.

So: when a rule matters, gate it in the command people actually run - LL0027 in the lessons registry. Adding a line here is the weakest available fix, and a rule stated here with no gate behind it should be read as a known-weak one.

What will refuse you

These block. Everything else in this file is guidance.

Gate Refuses
pre-commit + commit-msg hooks any guard failure; a multi-id subject with no Refs: trailer; a collapsed test suite
sprint plan a batch whose units lack Affects: or Points:, or exceed the split threshold
transition -> Done a story whose executable ACs have not passed, or that is past review.two_role_after without both review halves
transition -> Fixed a bug with no parseable Verification depth
sprint close units no independent pass covers; an unanswered checklist item
critic record a verdict carrying no brief provenance (--brief), unless stood down by a recorded config decision
critic signoff a principal the authoring session controls

Read the full file on GitHub · 252 lines

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.

  1. 4d ago First seen · 252 lines · 3,662 tokens per session scan A 57043c81e17c

Subscribe to this mod's changes

sdlc-studio AGENTS.md is an instructions file published in the GitHub repository DarrenBenson/sdlc-studio (21 stars, last pushed yesterday), licensed MIT. It adds 3,662 tokens to every session, about $0.0183 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.