spec

A command for turning a task request into a written specification. The specification records the intended result, testable acceptance criteria, exclusions, and unanswered questions.

In plain words
What is it for?
Use it with a tracker card, a conversation, or a TODO entry before planning or implementation.
Why use it?
It prevents work from starting with vague goals or unclear boundaries. Acceptance criteria are conditions a reviewer can objectively check.

Command

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 commands/tacoda/keystone/spec
Clone the repo
git clone --depth 1 https://github.com/tacoda/keystone
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 324 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 $0.00011 $0.00324
Opus 5 $0.00005 $0.00162
Sonnet 5 $0.00002 $0.00065
Haiku 4.5 $0.00001 $0.00032

Measured 2d ago against content hash bd7cf9b9923d, 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.

.charter/commands/spec.md · 33 lines

What it actually says

spec

Capture intent and acceptance criteria for a unit of work. First action on any task. Read .charter/guides/process/spec.md for the full discipline.

Inputs

  • A tracker card ID (Jira / Linear / GitHub Issues / Asana), or
  • A conversation describing the work, or
  • A TODO.md entry.

If a tracker card was named, fetch its description via whatever tooling the agent has (MCP server, gh issue view, jira CLI, web fetch). Copy any acceptance criteria into the spec.

Activities

  1. Restate the intent in your own words.
  2. List acceptance criteria — explicit, testable bullets a reviewer can verify objectively.
  3. List non-goals — what is not in scope, to prevent feature creep.
  4. Flag uncertainty — open questions the user must answer before planning.
  5. Save the spec to docs/specs/YYYY-MM-DD-<topic>.md with the frontmatter shape described in .charter/guides/process/spec.md (if the project has that location; otherwise capture inline in the chat).

Gate

Do not proceed to planning until the user has explicitly accepted the spec.

Iron law

No proceeding without explicit acceptance criteria. A spec that says "make X better" is not yet a spec.

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 · 33 lines · 11 tokens per session scan A bd7cf9b9923d

Subscribe to this mod's changes

spec is a command published in the GitHub repository tacoda/keystone (44 stars, last pushed 2mo ago), licensed MIT. It adds 11 tokens to every session and 324 once invoked, about $0.0001 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.