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/refresh.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/refresh)<a href="https://agentmods.dev/commands/nguyensitrung/conductor-beads/refresh"><img src="https://agentmods.dev/badge/commands/nguyensitrung/conductor-beads/refresh.svg" alt="Measured on agentmods" 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 | $0.01023 |
| Opus 5 | $0.00000 | $0.00511 |
| Sonnet 5 | $0.00000 | $0.00205 |
| Haiku 4.5 | $0.00000 | $0.00102 |
Grade A, and why
refresh 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 7d 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
97% identical to conductor-refresh — 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conductor Refresh
Sync conductor context documentation with the current codebase state.
1. Verify Setup
Check conductor/ exists with core files. If not, suggest /conductor-setup.
2. Determine Scope
If no argument, ask:
all- Full refreshtech- tech-stack.md onlyproduct- product.md onlyworkflow- workflow.md onlytrack [id]- Specific track
3. Analyze Drift
Compare current codebase against docs:
- Tech: Scan package.json, requirements.txt, etc. for new/removed deps
- Product: Check completed tracks not reflected in product.md
- Workflow: Check CI/CD changes, new tooling
4. Present Drift Report
Show what's changed since last setup/refresh.
5. Confirm Updates
Ask user to approve changes.
6. Apply Updates
- Create backups (*.md.bak)
- Update files with new information
- Add refresh marker to top of files
7. Update State
Create/update conductor/refresh_state.json with timestamp and changes.
8. Commit
git add conductor/
git commit -m "conductor(refresh): Sync context with codebase"
8a. CONSOLIDATE LEARNINGS (Pattern Flywheel)
PROTOCOL: Aggregate and consolidate learnings across all tracks into project patterns.
-
Scan All Track Learnings:
- Read
learnings.mdfrom all tracks inconductor/tracks/*/ - Read
learnings.mdfrom all archived tracks inconductor/archive/*/
- Read
-
Extract Pattern Candidates:
- Find patterns mentioned 2+ times across different tracks
- Find gotchas that reoccur
- Find context that applies project-wide
-
Present Consolidation Report:
"## Learnings Consolidation Report"
Patterns found across tracks:
Pattern Tracks Already in patterns.md? "Use Zod for validation" auth, api, users ❌ No "Barrel exports required" auth, config ✅ Yes New patterns to add: [list] Duplicate patterns to merge: [list]
"Would you like to update
conductor/patterns.md? (yes/no)"
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.
- 7d ago First seen · 142 lines · 0 tokens per session scan A ee1653e67763
refresh 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 1,023 tokens. A static security scan graded it A with 0 findings. It is 97% identical to conductor-refresh, 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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.