spec

A project-specific writing guide for creating or changing a spec, a document that describes how a system should behave. It follows the repository’s required format, terms, and review process.

In plain words
What is it for?
Use it to write a new spec, add requirements or scenarios, define behavior, or reorganize existing spec content.
Why use it?
It reduces guesswork about what belongs in a spec and helps keep new or changed requirements consistent with the codebase.

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/ambient-code/platform/spec
Any agent
npx skills add ambient-code/platform --skill spec
Clone the repo
git clone --depth 1 https://github.com/ambient-code/platform

Made for: Claude Code, Codex.

Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 718 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 $0.00087 $0.00718
Opus 5 $0.00044 $0.00359
Sonnet 5 $0.00017 $0.00144
Haiku 4.5 $0.00009 $0.00072

Measured 2d ago against content hash 2a20a921a6a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec 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.

skills/spec/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write or Modify a Spec

Help the user create or change a spec that describes desired system behavior.

User Input

$ARGUMENTS

Before Anything Else

Read these two files in full before proceeding:

  1. specs/index.spec.md — what a spec is, the required format, naming conventions, and what does and does not belong
  2. workflows/specs/spec-change.workflow.md — the full spec change workflow (framing, grounding, drafting, critic passes, synthesis)

Then follow the workflow phases in order.

Steps

Phase 1 — Frame

Establish the framing before writing anything:

  • Desired state only. Ask the user what the system should do, not what's currently broken. If they describe a bug, redirect: "What should the correct behavior be?"
  • Scope boundary. Which components does this change touch? (schema, gRPC, runner, operator, CLI, frontend, SDK, RBAC)
  • Reserved terms check. Verify no collision with Ambient domain model terms (Inbox, Session, Agent, Project, Credential, SessionMessage, etc.)

Phase 2 — Ground in the codebase

Read actual code and existing specs in the affected areas. Confirm your understanding without wasting the user's time:

  • Read existing specs in the target domain
  • Grep the components identified in Phase 1
  • Summarize back in 3–5 sentences: what you found, what you believe they want, what's ambiguous
  • Ask only where the codebase doesn't give a clear answer

Do not proceed to drafting until the user confirms.

Phase 3 — Draft the Spec

Follow the format from specs/index.spec.md:

  • Purpose section — one paragraph describing the domain or feature
  • Requirements — each states an observable behavior using RFC 2119 keywords (SHALL, MUST, SHOULD, MAY)
  • Scenarios — concrete Given/When/Then examples for each requirement that could be turned into tests

Include: data model, write paths, read paths, RBAC, migration plan for all existing consumers.

Phase 4 — Critic Pass

Spawn critics in parallel per the workflow. Standard critics (every spec change):

  • Schema / migration
  • RBAC / auth
  • Ambient terminology

Read the full file on GitHub · 83 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 83 lines · 87 tokens per session scan A 2a20a921a6a0

Subscribe to this mod's changes

spec is a skill published in the GitHub repository ambient-code/platform (129 stars, last pushed 2d ago), licensed MIT. It adds 87 tokens to every session and 718 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 2026-08-30.

Related

Other skills, from other repositories

peekaboo

Capture and automate macOS UI with the Peekaboo CLI.

the-open-agent/openagent · 17 tokens

powerpoint

Create designed, editable PowerPoint .pptx presentations with PptxGenJS. Use when the user asks to create, generate, update, or inspect a deck, slide deck, presentation, or .pptx file.

the-open-agent/openagent · 48 tokens

argent-tv-interact

Control and inspect TV apps via argent — Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…

software-mansion/argent · 107 tokens

review-offered-task

Review a task that has been offered to you and decide whether to accept or reject it.

desplega-ai/agent-swarm · 22 tokens

company-hiring-intelligence

Reverse-engineer what a company is building by scraping their job postings, careers page, LinkedIn Jobs, and engineering blog using TinyFish web agents. Use whenever a user wants to understand a company's strategic direction from hiring signals, do competitive intelligence, figure out a tech stack from job…

tinyfish-io/tinyfish-cookbook · 169 tokens

aidd-dev:08:for-sure

Iterative agent loop that tracks attempts and retries until a success condition is met. Use when the user says "for sure", "make sure", "keep trying until", "loop until done", "don't stop until", or needs guaranteed completion of a task with explicit success criteria.

ai-driven-dev/framework · 66 tokens