A tool for keeping a project’s living specification aligned with code that has actually been merged. It groups implemented behavior by feature area rather than by sprint or backlog item.

Use it after repository synchronization or when the user asks to update the project specification. It records current feature behavior and links it to the backlog items that delivered it.

It prevents the specification from describing planned or outdated behavior. It checks whether new merges exist before doing work and uses acceptance criteria and diffs when the behavior is unclear.

update-spec — Skill for Claude Code by atman-33

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.

Any agent

npx skills add atman-33/workhub --skill update-spec

Clone the repo

git clone --depth 1 https://github.com/atman-33/workhub

Made for: Claude Code.

Or install team-ops, the plugin that ships this one along with the rest of its 13 skills.

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/atman-33/workhub/update-spec.svg)](https://agentmods.dev/skills/atman-33/workhub/update-spec)

Your own site

<a href="https://agentmods.dev/skills/atman-33/workhub/update-spec"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/update-spec.svg" alt="Measured on agentmods" height="20"></a>

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 543 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00056	$0.00543
Opus 5	$0.00028	$0.00271
Sonnet 5	$0.00011	$0.00109
Haiku 4.5	$0.00006	$0.00054

Measured 4d ago against content hash c3769ed33618, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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.

plugins/team-ops/skills/update-spec/SKILL.md · 43 lines

What it actually says

Update the living spec

docs/spec/spec.md answers "what is implemented today, by feature area" — kept truthful by folding in what actually merged, not what was planned.

Steps

Check there is anything to do: compare each repo's repo-state.json.lastSyncAt / new commits.jsonl entries against the spec's last-updated marker (an HTML comment at the top of spec.md, e.g. ). No new merges since the marker → stop and report "no change" — this is what keeps the daily routine cheap.
Gather what merged: new commits per repo grouped by PBI id (pbi-activity.json + commits.jsonl), and for each involved PBI its ## Acceptance Criteria (satisfied AC = implemented behavior). Inspect actual diffs in the script-owned mirror (git -C <mirrorPath> show <sha>) only where the commit subject + AC leave the behavior unclear.
Fold into spec.md (team content language):
- Organized by feature area (grow headings as the product grows), not by sprint or PBI — a newcomer reads it as "how the product works".
- Update the areas the merged PBIs touched; state current behavior, and reference source PBIs inline ((P-0012)) for traceability.
- Move superseded statements out — the spec describes the present, the git history keeps the past.
- Refresh the last-updated marker with today's date and each repo's synced tip sha.
Append an activity-log line (- <date> [...] update-spec: folded P-0012, P-0015 into spec.md).

Rules

Never describe unmerged work as implemented. Planned work lives in the backlog, not the spec.
When spec.md outgrows one file, split into docs/spec/<area>.md with spec.md as the index — propose this to the user first.

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 · 43 lines · 56 tokens per session scan A c3769ed33618

Subscribe to this mod's changes

update-spec is a skill published in the GitHub repository atman-33/workhub (2 stars, last pushed 2d ago), licensed MIT. It adds 56 tokens to every session and 543 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 2026-09-03.

Claude Code Project management Writing and docs claude-code-plugin cross-platform desktop-app developer-tools obsidian

tasks

A task-breakdown tool that turns a plan, specification, feature brief, bug report, technical-debt item, or chore into small TASK-NNN work items. Technical debt means postponed cleanup or design work in a codebase.

cryndoc/polisade-orchestrator · 127 tokens

prd

A Product Requirements Document (PRD) writer for large software initiatives. A PRD records the problem, goals, requirements, assumptions, and evidence before implementation begins.

cryndoc/polisade-orchestrator · 121 tokens

roadmap

An implementation plan made from a technical specification, organized into phases, milestones, and dependencies.

cryndoc/polisade-orchestrator · 109 tokens

pr

A command for managing pull requests on GitHub or Bitbucket Server. A pull request is a request for other developers to review and merge changes into a project branch.

cryndoc/polisade-orchestrator · 150 tokens

shipyard-writing-plans

Use when you have a spec, requirements, or design for a multi-step task — before touching code. Also triggers on "plan this", "break this down", "create tasks", "decompose this feature", or when a task clearly needs more than 2-3 steps to implement. If you're about to start building without a plan, or writing vague…

lgbarn/shipyard · 96 tokens

sync

Rebuild PROJECTSTATE derived fields from artifact files.

cryndoc/polisade-orchestrator · 11 tokens