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/fredantb/spec-driven-development/claude-mdgit clone --depth 1 https://github.com/FredAntB/Spec-Driven-DevelopmentWhat 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 | $0.00459 | $0.00459 |
| Opus 5 | $0.00230 | $0.00230 |
| Sonnet 5 | $0.00092 | $0.00092 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
Spec-Driven-Development 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 2d 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.
What it actually says
CLAUDE.md
Auto-read by Claude Code at session start.
Generated by the spec-driven-development skill.
Session startup — read in this order
-
If
CONTEXT.mdexists — read it first- Resume the active task from the resume block
- Announce which session this is and what you're picking up
- Do not ask what to work on unless the user interrupts
-
Read
requirements.md— the contract for what the system does -
Read
design.md— the blueprint for how it is built -
Read
tasks.md— find the next incomplete[ ]task
If none of these files exist yet, the project has not been specced. Offer to run the SDD skill interview to create them.
Hard constraints
- Never implement requirements not in requirements.md
- Never alter the data model without updating design.md first
- Never create files not listed or implied in design.md
- Never mark a task
[x]without verifying its acceptance criterion - Never guess when a requirement is ambiguous — ask instead
Divergence protocol
If implementation must deviate from design.md:
- Stop
- Describe the conflict clearly
- Wait for explicit user approval
- Update design.md FIRST, then implement
- Record the divergence in CONTEXT.md
CONTEXT.md update rules
At the end of each session (or at a natural stopping point):
- Add a session log row: date, one-line summary, files changed
- Update the resume block with the next active task
- Record any divergences from design.md
- Resolve any open questions that were answered
At the start of each session:
- Read CONTEXT.md before doing anything else
- Announce: "Session [N] resuming. Last worked on [task]. Picking up at [task]."
Skill mode
If the user wants to generate or update spec files, or set up AI config files, apply the full SDD skill from SKILL.md (if present in this folder). Otherwise operate as a spec-aware coding assistant using the existing files.
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.
- 2d ago First seen · 63 lines · 459 tokens per session scan A 35b69b04272c
Spec-Driven-Development CLAUDE.md is an instructions file published in the GitHub repository FredAntB/Spec-Driven-Development (152 stars, last pushed 3mo ago), licensed MIT. It adds 459 tokens to every session, about $0.0023 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 2026-08-30.
Other instructions, from other repositories
gortex CLAUDE.md
Claude Code instructions for zzet/gortex, covering gortex, build & test, codebase overview, discovery (read once, then keep using) and llm provider (powers ask and searchsymbols assist: modes).
mcp-unity AGENTS.md
Instructions for CoderGamester/mcp-unity, covering mcp unity — ai agent guide (mcp package), purpose (what this repo is), how it works (high-level data flow), key defaults & invariants and repo layout (where to change what).
mcp-server-azure-devops AGENTS.md
Instructions for Tiberriver256/mcp-server-azure-devops: /home/tiberriver256/repos/mcp-server-azure-devops/docs/important-knowledge/azure-devops-rest-api-research.md Researching Azure DevOps REST APIs, selecting api-version, or handling Azure DevOps Server (on-prem) endpoints.
rosetta AGENTS.md
Instructions for griddynamics/rosetta: Main goal: cover E2E AI PDLC engineering workflows at foundation level for AI-First SDLC in enterprise. Top-level or orchestrator agents MUST READ docs/ARCHITECTURE.md contains technical details and guidance, and docs/CONTEXT.md - business context. Subagents - when needed.…
rails-ai-context AGENTS.md
Instructions for crisnahine/rails-ai-context, covering rails-ai-context, agent skills, issue tracker, triage labels and domain docs.
inspecto CLAUDE.md
Instructions for inspecto-dev/inspecto, covering inspecto — claude code development guide, project overview, monorepo structure, development phases (load each file as needed) and key architectural decisions.