A workflow for recording an architectural decision before applying it to a project’s specifications, product requirements, development phases and task tracker.

Use it to draft one architecture decision, review it, preview the resulting document changes and apply an accepted decision across the project records.

It lets a decision be reviewed as a temporary record before project documents are changed. Applying it uses a resumable process so the related updates can be previewed and carried out together.

update-spec — Skill for Claude Code and Codex by firatcand: A workflow for recording an architectural decision before applying…

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/firatcand/forge/update-spec

Any agent

npx skills add firatcand/forge --skill update-spec

Clone the repo

git clone --depth 1 https://github.com/firatcand/forge

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/firatcand/forge/update-spec.svg)](https://agentmods.dev/skills/firatcand/forge/update-spec)

Your own site

<a href="https://agentmods.dev/skills/firatcand/forge/update-spec"><img src="https://agentmods.dev/badge/skills/firatcand/forge/update-spec.svg" alt="Measured on agentmods" height="20"></a>

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,830 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.

Model	Per session	Once invoked
Fable 5	$0.00050	$0.03830
Opus 5	$0.00025	$0.01915
Sonnet 5	$0.00010	$0.00766
Haiku 4.5	$0.00005	$0.00383

Measured 4d ago against content hash e98282b86109, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

update-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 4d 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/update-spec/SKILL.md · 214 lines

How it starts

The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/update-spec

Two modes, one lifecycle (ephemeral ADRs — see .forge/CONTEXT.md §Ephemeral ADR workflow):

--draft — interview → write spec/decisions/<YYYY-MM-DD>-<slug>.md from templates/adr.template.md. The user reviews, optionally gets a second opinion, and flips status: accepted by hand.
--apply <slug> (+ --yes-all, --resume, --dry-run) — author the payload-complete journal, preview every artifact diff, then delegate ALL mutation to forge orchestrate apply-decision. On success the skill (not the verb) runs the git commit with the ADR's rationale as the body.

Skill ↔ verb contract: this skill owns interviews, diff previews, confirmations, journal authoring (the verb's documented upstream input), and git. The verb owns every artifact mutation, the resumable journal state machine, INDEX.md, and ADR deletion. The skill NEVER edits SPEC/PRD/phases/tracker directly.

Mode `--draft`

Preflight

templates/adr.template.md must exist. Missing → stop: "run forge migrate (or forge upgrade) to restore the bundled scaffold."
One decision at a time. Scan spec/decisions/*.md and classify each file:
- INDEX.md → ignore (the durable decision index).
- ADR frontmatter parses with status: proposed or status: accepted → refuse:
```
✗ /update-spec --draft: an active ADR already exists: <file> (status: <status>).
  Finish it first: /update-spec --apply <slug>   (or edit/delete the draft)
```
- status: rejected → refuse with: "delete the rejected ADR manually (SPEC lifecycle: rejected ADRs are removed by hand, never applied or replaced)."
- Filename matches the ADR shape <YYYY-MM-DD>-<slug>.md but the frontmatter is missing or unparseable → REFUSE ("malformed ADR — fix or remove it first"). A broken ADR must not be silently treated as a companion note and bypassed.
- Anything else (no ADR-shaped name, no frontmatter — e.g. companion *.plan.md notes) → ignore; companions never block.

Read the full file on GitHub · 214 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.

4d ago First seen · 214 lines · 50 tokens per session scan A e98282b86109

Subscribe to this mod's changes

update-spec is a skill published in the GitHub repository firatcand/forge (13 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 3,830 once invoked, about $0.0003 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.

Planning Writing and docs agentic-coding ai-coding-agent claude-code codex compound-engineering spec-driven-development

ospec-change

Create or advance a lightweight OSpec change using the classic fast workflow.

clawplays/ospec · 18 tokens

prospec-knowledge-generate

Generate AI Knowledge - Read raw-scan.md, analyze project structure, autonomously decide module boundaries, and produce Recipe-First module READMEs and index. Triggers: generate knowledge, analyze project, module split, 產生知識, 知識庫, 分析專案, 模組拆分.

benwu95/prospec · 71 tokens

submit-pr

Open a prospec pull request in the house format — push the change's two commits, write the Traditional Chinese body, and link it to its issue. Triggers: submit pr, open pr, 開 PR, 送 PR, 發 PR, pull request, 提交 PR.

benwu95/prospec · 59 tokens

submit-issue

Open a prospec GitHub issue in the house format — conventional-commit title, Traditional Chinese body (problem → solutions → acceptance criteria), downstream-compatibility block, series cross-links, and optional model-routing guidance. Triggers: submit issue, open issue, create issue, file issue, 開 issue, 發 issue, 建…

benwu95/prospec · 77 tokens

prospec-explore

Explore - Requirement exploration, problem investigation, and solution comparison partner. Triggers: explore, compare, investigate, unsure, clarify, 探索, 比較, 釐清, 調查, 不確定.

benwu95/prospec · 50 tokens

prospec-plan

Plan Implementation - Convert User Story into technical implementation plan (plan.md) and change specification (delta-spec.md). Triggers: plan, architecture, technical plan, 規劃, 架構規劃, 技術規劃.

benwu95/prospec · 53 tokens