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/hundia/autospec/claude-mdgit clone --depth 1 https://github.com/Hundia/autospecWrote 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/hundia/autospec/claude-md)<a href="https://agentmods.dev/instructions/hundia/autospec/claude-md"><img src="https://agentmods.dev/badge/instructions/hundia/autospec/claude-md.svg" alt="Measured on agentmods" 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 | $0.00902 | $0.00902 |
| Opus 5 | $0.00451 | $0.00451 |
| Sonnet 5 | $0.00180 | $0.00180 |
| Haiku 4.5 | $0.00090 | $0.00090 |
Grade A, and why
autospec CLAUDE.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 5d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Memory — AutoSpec
About This Project
AutoSpec is a Spec-Driven Development (SDD) framework. This project develops itself using its own tools. Use /sprint-run, /execute-ticket, /sprint-status etc. in Claude Code.
MANDATORY Development Workflow
Rule 1: Backlog-First Development
Every fix, feature, or change MUST be tracked in specs/backlog.md before or during implementation:
- Determine if this is a bug (B.XX), new feature, or enhancement
- Add ticket to
specs/backlog.mdin the appropriate sprint section - Set status to 🔄 In Progress when starting
- Set status to ✅ Done when complete
Skip ONLY when user explicitly says "skip backlog", "don't track this"
Rule 2: Living Documentation
Every implemented feature MUST update docs/:
- Viewer changes →
docs/viewer/ - CLI changes →
docs/cli/ - Methodology changes →
docs/methodology/ - Deployment changes →
docs/deployment/ - New subsystem → create new
docs/<subsystem>/directory
Rule 3: QA Before Done
No ticket is ✅ Done without verification:
| Change Type | QA Required |
|---|---|
| Bug fix | Reproduce first, fix, verify user flow passes |
| CLI change | npm run build + npm test in cli/ |
| Viewer change | npm run build in viewer/ + visual check |
| Docs/config only | No QA — mark ✅ directly |
| New feature | Full test suite + new test cases if needed |
Rule 4: Orchestrator + Agent Execution Pattern
This project uses Opus 4.6 as Orchestrator + Sonnet 4.6 as Sprint Agents:
- Orchestrator writes
agents/sprint-X-brief.mdbefore spawning - Orchestrator spawns:
Agent(subagent_type=general-purpose)with briefing - Agent reads brief + relevant specs + docs, implements tickets
- Agent updates:
specs/backlog.md(🔲→✅), docs/,sprints/sprint-X/summary.md - Orchestrator reviews summary, spawns next sprint(s)
Parallel execution: Sprints with no dependencies run as parallel agents in one message.
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.
- 5d ago First seen · 102 lines · 902 tokens per session scan A 663de70bbf0a
autospec CLAUDE.md is an instructions file published in the GitHub repository Hundia/autospec (4 stars, last pushed 2mo ago), licensed MIT. It adds 902 tokens to every session, about $0.0045 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
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).