spec-sync

spec-sync is a skill for Claude Code, Codex from CorvidLabs/agent-3md. It costs 78 tokens per session (1,049 once invoked), scanned A, original, MIT.

A workflow for keeping Markdown module specifications in sync with their source code. It also manages related files such as requirements, tasks, design, context, and testing notes.

In plain words
What is it for?
Use it when creating, editing, or reviewing code in a module with a specification. It helps track requirements, work items, design decisions, and test plans.
Why use it?
It reduces the risk that documentation and code describe different behavior. It gives changes a defined process for updating and checking both sides.

Skill for Claude CodeCodex

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 skills/corvidlabs/agent-3md/spec-sync
Any agent
npx skills add CorvidLabs/agent-3md --skill spec-sync
Clone the repo
git clone --depth 1 https://github.com/CorvidLabs/agent-3md

Made for: Claude Code, Codex.

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 spec-sync

README.md
[![agentmods](https://agentmods.dev/badge/skills/corvidlabs/agent-3md/spec-sync.svg)](https://agentmods.dev/skills/corvidlabs/agent-3md/spec-sync)
Your own site
<a href="https://agentmods.dev/skills/corvidlabs/agent-3md/spec-sync"><img src="https://agentmods.dev/badge/skills/corvidlabs/agent-3md/spec-sync.svg" alt="Measured on agentmods" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,049 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00078 $0.01049
Opus 5 $0.00039 $0.00524
Sonnet 5 $0.00016 $0.00210
Haiku 4.5 $0.00008 $0.00105

Measured 3d ago against content hash da4dc22433b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-sync 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 3d 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.

.claude/skills/spec-sync/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec-Sync Workflow

This project uses spec-sync for bidirectional spec-to-code validation. Specs live in specs/<module>/<module>.spec.md.

Companion files

Each canonical spec may have policy-selected companion files. Read and update the ones present; do not create empty companions only for ceremony:

  • tasks.md — Work items for this module. Check off tasks (- [x]) as you complete them. Add new tasks if you discover work needed.
  • requirements.md — Acceptance criteria and user stories. These are permanent invariants, not tasks — do not check them off. Update if requirements change.
  • context.md — Architectural decisions, key files, and current status. Update when you make design decisions or change what's in progress.
  • testing.md — Test strategy: automated test locations, manual QA checklists, and edge cases/boundary conditions.
  • design.md (opt-in) — Layout, component hierarchy, design tokens, and asset references. Present when companions.design is enabled in config.

Verified SDD change lifecycle (5.0)

For every meaningful source, test, public documentation, schema, or configuration change:

  1. Run specsync change new "<intent>" --json and conduct the returned interview with the user.
  2. Use specsync change answer <id> <question-id> <answer> --json until no questions remain.
  3. Complete the adaptively selected artifacts and semantic deltas. Requirements use stable REQ-<module>-<number> IDs, a normative SHALL statement, and acceptance criteria.
  4. Ask the user for the definition approval, then run specsync change approve <id>.
  5. Run specsync change start <id> before editing implementation code.
  6. Keep tasks and artifacts current, then run specsync change verify <id>.
  7. Present verification evidence and ask for closing approval. Only after explicit approval, run specsync change accept <id>; archive separately with specsync change archive <id>.

Never invent or self-grant either human approval. If an approved definition changes, its digest becomes stale and must be approved again. specsync check validates canonical specs plus approved active deltas, requirement-to-test evidence, change coverage, and CI gates.

Read the full file on GitHub · 76 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. 3d ago First seen · 76 lines · 78 tokens per session scan A da4dc22433b7

Subscribe to this mod's changes

spec-sync is a skill published in the GitHub repository CorvidLabs/agent-3md (1 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 1,049 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

agent-framework-py-release

Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…

microsoft/agent-framework · 103 tokens

python-package-management

Guide for managing packages in the Agent Framework Python monorepo, including creating new connector packages, versioning, and the lazy-loading pattern. Use this when adding, modifying, or releasing packages.

microsoft/agent-framework · 43 tokens

foundry-hosted-agent-validation

Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.

microsoft/agent-framework · 82 tokens

python-feature-lifecycle

Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.

microsoft/agent-framework · 43 tokens

build-and-test

How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.

microsoft/agent-framework · 26 tokens

python-code-quality

Code quality checks, linting, formatting, and type checking commands for the Agent Framework Python codebase. Use this when running checks, fixing lint errors, or troubleshooting CI failures.

microsoft/agent-framework · 40 tokens