speckit.spex-collab.revise

speckit.spex-collab.revise is a command for Claude Code from rhuss/cc-spex. It costs 23 tokens per session (2,424 once invoked), scanned A, original, Apache-2.0.

A workflow for updating a software specification after pull-request review feedback. A pull request is a proposed code change for others to review; the workflow also updates the related plan, task list, and revision history.

In plain words
What is it for?
Use it to gather review comments from a pull request, revise spec.md, cascade changes to planning files, record the revision in REVIEWERS.md, and update the pull request.
Why use it?
It keeps the written requirements and implementation plan aligned with decisions made during code review.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions subagents; mentions Claude Code.

Part of the spex plugin — 1 skill, 7 commands shipped together

Good fit Use it to gather review comments from a pull request, revise spec.md, cascade changes to planning files, record the revision in REVIEWERS.md, and update the pull request.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/rhuss/cc-spex/speckit.spex-collab.revise
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.

Clone the repo
git clone --depth 1 https://github.com/rhuss/cc-spex

Made for: Claude Code.

Or install spex, the plugin that ships this one along with the rest of its 1 skill, 7 commands.

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 speckit.spex-collab.revise

README.md
[![agentmods](https://agentmods.dev/badge/commands/rhuss/cc-spex/speckit.spex-collab.revise/github.svg)](https://agentmods.dev/commands/rhuss/cc-spex/speckit.spex-collab.revise)
Your own site
<a href="https://agentmods.dev/commands/rhuss/cc-spex/speckit.spex-collab.revise"><img src="https://agentmods.dev/badge/commands/rhuss/cc-spex/speckit.spex-collab.revise/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for speckit.spex-collab.revise

Your own site · 80×15
<a href="https://agentmods.dev/commands/rhuss/cc-spex/speckit.spex-collab.revise"><img src="https://agentmods.dev/badge/commands/rhuss/cc-spex/speckit.spex-collab.revise.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,424 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00023 $0.02424
Opus 5 $0.00012 $0.01212
Sonnet 5 $0.00005 $0.00485
Haiku 4.5 $0.00002 $0.00242

Measured 10d ago against content hash f5aeff93a5e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

speckit.spex-collab.revise 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 10d 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.

spex/extensions/spex-collab/commands/speckit.spex-collab.revise.md · 322 lines

How it starts

The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Revise Spec from PR Feedback

Handles the spec revision loop: read PR review comments, update spec, cascade to plan and tasks, document the revision in REVIEWERS.md, and push back to the PR.

Ship Pipeline Guard

If .specify/.spex-state exists with mode: "ship", return immediately. Spec revision is an interactive collab workflow.

Resolve Context

PREREQ=$(.specify/scripts/bash/check-prerequisites.sh --json --paths-only 2>/dev/null)
FEATURE_DIR=$(echo "$PREREQ" | jq -r '.FEATURE_DIR')
BRANCH=$(git branch --show-current)

Verify required artifacts exist:

[ -f "${FEATURE_DIR}/spec.md" ] || { echo "ERROR: No spec.md found in ${FEATURE_DIR}"; exit 1; }

Gather Feedback

Determine the review feedback to address. Two input modes:

Mode 1: PR number provided (--pr <number>)

Fetch unresolved review comments from the PR:

PR_NUM="<number>"
gh pr view "$PR_NUM" --json reviews,comments --jq '.reviews[].body, .comments[].body' 2>/dev/null
gh api "repos/{owner}/{repo}/pulls/${PR_NUM}/comments" --jq '.[] | select(.position != null) | "\(.path):\(.position) - \(.body)"' 2>/dev/null

Present a summary of the feedback to the user:

## PR #<number> Review Feedback

Found N review comments:

1. @reviewer: "The hard removal of stdout seems risky..."
2. @reviewer: "Should subagent merging be in scope?"
...

Which comments should we address in this revision?

{harness:interactive-choice} (multi-select, header: "Feedback"): "Which review comments should this revision address?"

Options: one per comment (label: truncated comment, description: full text)

Mode 2: User describes changes (arguments or conversation)

If no --pr flag, the user's arguments or conversation describe what to change. Use that directly as the revision input.

Plan the Revision

Before making changes, summarize what will change. Read the current spec.md and identify which sections are affected by the feedback.

Present a revision plan:

## Revision Plan

Based on the feedback, these changes are needed:

**Spec changes**:
- Section "Requirements": add deprecation warning for stdout access
- Section "Out of Scope": move subagent merging to in-scope

**Expected cascade**:
- plan.md: will need regeneration (new requirements affect implementation approach)
- tasks.md: will need regeneration (task count may change)
- REVIEWERS.md: Key Decisions and Scope Boundaries sections affected

Proceed with revision?

Read the full file on GitHub · 322 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. 10d ago First seen · 322 lines · 23 tokens per session scan A f5aeff93a5e7

Subscribe to this mod's changes

speckit.spex-collab.revise is a command published in the GitHub repository rhuss/cc-spex (117 stars, last pushed 21d ago), licensed Apache-2.0. It adds 23 tokens to every session and 2,424 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.