Borrowing it
Nothing to install: this file belongs to NguyenSiTrung/Conductor-Beads. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/NguyenSiTrung/Conductor-Beads/main/.claude/skills/conductor/references/commands/revise.mdgit clone --depth 1 https://github.com/NguyenSiTrung/Conductor-BeadsWrote 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.
[](https://agentmods.dev/commands/nguyensitrung/conductor-beads/revise)<a href="https://agentmods.dev/commands/nguyensitrung/conductor-beads/revise"><img src="https://agentmods.dev/badge/commands/nguyensitrung/conductor-beads/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.
<a href="https://agentmods.dev/commands/nguyensitrung/conductor-beads/revise"><img src="https://agentmods.dev/badge/commands/nguyensitrung/conductor-beads/revise.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.01442 |
| Opus 5 | $0.00000 | $0.00721 |
| Sonnet 5 | $0.00000 | $0.00288 |
| Haiku 4.5 | $0.00000 | $0.00144 |
Grade A, and why
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.
This is a copy
95% identical to conductor-revise — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conductor Revise
Update specifications and plans when implementation reveals issues, requirements change, or scope adjustments are needed.
1. Identify Track
- Find active track (marked
[~]in tracks.md) - If no active track, ask which track to revise
- Check for
parallel_state.json(parallel execution in progress)
1a. Parallel Execution Check
If parallel_state.json exists:
"⚠️ This track has parallel workers currently running." "Revising the plan may affect in-progress workers."
"A) Wait for workers to complete, then revise" "B) Revise now (affected workers may need restart)" "C) Cancel revision"
- If A: Monitor until complete, then proceed
- If B: Note affected tasks in revision, workers operating on changed tasks should abort
- If C: HALT
2. Determine Revision Type
Ask what needs revision:
- Spec - Requirements changed or misunderstood
- Plan - Tasks need to be added, removed, or modified
- Both - Significant scope change
3. Gather Context
Ask targeted questions about what was discovered and what needs to change.
4. Create Revision Record
Append to conductor/tracks/<track_id>/revisions.md:
- Revision number, date, type
- What triggered the revision
- Current phase/task when revision occurred
- Changes made (spec and/or plan)
- Rationale and impact
5. Update Documents
- Update
spec.mdand/orplan.mdas needed - Add "Last Revised" marker at top of updated files
- New tasks:
[ ], Removed tasks:[-] [REMOVED: reason] - Phase-level parallel changes:
- Add/modify
<!-- depends: -->annotations for phase dependencies - Add/modify
<!-- depends: phase1, phase2 -->for specific phase dependencies - If removing a phase that others depend on, update dependent phases
- Add/modify
- Task-level parallel changes:
- Update
<!-- files: ... -->and<!-- depends: ... -->annotations - If parallel phase removed: Mark for sequential execution or update annotations
- Update
6. Commit
git add conductor/tracks/<track_id>/
git commit -m "conductor(revise): Update spec/plan for <track_id>"
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.
- 10d ago First seen · 156 lines · 0 tokens per session scan A d83d67e41611
revise is a command published in the GitHub repository NguyenSiTrung/Conductor-Beads (24 stars, last pushed 6mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,442 tokens. A static security scan graded it A with 0 findings. It is 95% identical to conductor-revise, differing in 4 lines, and is treated as a copy.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.