agentmods.dev

ai-sdlc CLAUDE.md

ai-sdlc CLAUDE.md is an instructions file for coding agents from ai-sdlc-framework/ai-sdlc. It costs 13,939 tokens per session, scanned A, original, Apache-2.0.

Project instructions for AI-SDLC, a framework that automates and governs software development workflows across branches, reviews, and pipeline stages.

In plain words
What is it for?
Use them when working on AI-SDLC branches, rebasing pull requests, resolving workflow-related conflicts, or changing its plugin, pipeline, orchestrator, or governance code.
Why use it?
They define the repository’s workflow for keeping feature branches current and preserving a linear Git history. They also describe how its tools handle rebasing, conflicts, attestations, and verification.

Instructions file

not rated 103 +12 changed today A scan 13,939 tokens original Apache-2.0
View the source file ai-sdlc-framework/ai-sdlc
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/ai-sdlc-framework/ai-sdlc/claude-md
Clone the repo
git clone --depth 1 https://github.com/ai-sdlc-framework/ai-sdlc

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 ai-sdlc CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ai-sdlc-framework/ai-sdlc/claude-md.svg)](https://agentmods.dev/instructions/ai-sdlc-framework/ai-sdlc/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ai-sdlc-framework/ai-sdlc/claude-md"><img src="https://agentmods.dev/badge/instructions/ai-sdlc-framework/ai-sdlc/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 13,939 This file is loaded in full into every session.
When invoked 13,939 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 $0.13939 $0.13939
Opus 5 $0.06970 $0.06970
Sonnet 5 $0.02788 $0.02788
Haiku 4.5 $0.01394 $0.01394

Measured today against content hash 83d20c28a109, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-sdlc CLAUDE.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 today.

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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- `claude` — **(DEFAULT since AISDLC-352)** shells out to `claude -p` via `child_process.spawn`. **Use this for autonomous tick from a shell** (cron/daemon/sidecar context where no slash command body is around). Billing:
CLAUDE.md · 454 lines

How it starts

The opening of the file, as written. The whole thing — 454 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI-SDLC Project Instructions

Scope: AI-SDLC is a full autonomous SDLC framework — autonomous orchestrator (RFC-0015), cross-harness review (RFC-0010 §13), decision engine (RFC-0011 DoR), operator TUI (RFC-0023), Pattern-C worktree isolation, and declarative governance. The ai-sdlc-plugin/ package is the Claude Code plugin pillar; pipeline-cli/ is the Step 0-13 pipeline runtime; orchestrator/ is the CLI and agent runner layer.

Git Flow

  • Always rebase feature branches onto main; never merge main in.
  • Update branch: git fetch origin && git rebase origin/main, then git push --force-with-lease.
  • Never gh api pulls/N/update-branch with merge method. Keep linear history.
  • /ai-sdlc rebase <pr> automates mechanical conflicts (test additions to same describe, prettier drift) and re-signs the attestation only when contentHash changed. Escalates semantic conflicts, modify-vs-delete, verification failures, and 3-attempt iteration cap. Refuses force-push to main/master. CHANGELOG.md conflicts should not arise on feature branches — if a rebase surfaces one, remove the CHANGELOG change from the feature branch rather than merging both sides (AISDLC-401).

CI marker hygiene

GitHub Actions silently skips ALL workflows when ANY commit body contains [skip ci], [ci skip], [no ci], [skip actions], or [actions skip] (substring, case-insensitive). Use the paren-quoted form (skip ci marker) in commit messages. Backtick-wrapping does NOT defeat the parser. scripts/check-skip-ci-marker.sh enforces on push.

Branches & Commits

  • Branches: feat/<desc>, fix/<desc>, or ai-sdlc/issue-<n>.
  • Conventional commits (feat:, fix:, test:, docs:, chore:, style:).
  • Include Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>.

PRs

  • Never merge PRs — only humans merge.
  • Never close issues or PRs. Never force-push to main/master.
  • Dismiss stale reviews only with documented reason (truncation, API errors).
  • auto-enable-auto-merge.yml sets --auto --squash on same-repo PRs (AISDLC-400: merge queue dropped 2026-05-23; explicit --squash ensures PRs always land as one commit on main regardless of repo-default drift). Setting --auto is NOT merging. PRs merge directly once ai-sdlc/pr-ready + Backlog Drift required checks pass — no merge-queue serialization, no update-branch CI re-run. AISDLC-398's content-addressed envelopes (headBlobSha-based, base-independent) eliminate v4-kick permanently. See docs/operations/merge-without-queue.md for the full flow and rollback procedure.

Read the full file on GitHub · 454 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. today Changed · +73 tokens per session 83d20c28a109
  2. 5d ago First seen · 454 lines · 13,866 tokens per session scan A b928f709f265

Subscribe to this mod's changes

ai-sdlc CLAUDE.md is an instructions file published in the GitHub repository ai-sdlc-framework/ai-sdlc (103 stars, last pushed today), licensed Apache-2.0. It adds 13,939 tokens to every session, about $0.0697 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

CI and CDCommitsDevOps and cloudGit and workflowGoai-agentsai-coding-agentsai-governancedeveloper-tools
Related

Other instructions, from other repositories

ai-agents push-lock.instructions.md

Instructions for rjmurillo/ai-agents, covering one push lock path, must, must not, historical measurements and commit guard.

rjmurillo/ai-agents · 2,104 tokens

martin-loop AGENTS.md

AGENTS.md instructions for Keesan12/martin-loop, covering martinloop agent operating rules, repository authority, mandatory internal-first sequence, prohibited actions and required internal health proof.

Keesan12/martin-loop · 1,999 tokens

toolhive-registry-server CLAUDE.md

Claude Code instructions for stacklok/toolhive-registry-server, covering claude.md, design rules, available subagents, core development agents and support agents.

stacklok/toolhive-registry-server · 2,470 tokens

uzomuzo-oss CLAUDE.md

Claude Code instructions for future-architect/uzomuzo-oss, covering claude.md, worktree isolation (must read first), build & test, configuration and go version policy.

future-architect/uzomuzo-oss · 643 tokens

martin-loop CLAUDE.md

Claude Code instructions for Keesan12/martin-loop, covering claude code instructions, current working status — 2026-08-11, working now, fixed in the current fixes branch and still not complete.

Keesan12/martin-loop · 573 tokens

agent-engineering-standards AGENTS.md

AGENTS.md instructions for onesimplecode/agent-engineering-standards, covering agents.md — public agent conventions, core rules, requirements syntax, data routing (tr-sec-003) and loop contracts (tr-agt-003).

onesimplecode/agent-engineering-standards · 7,802 tokens