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.
git clone --depth 1 https://github.com/Jinghao67/conductorWrote 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/agents/jinghao67/conductor/cd-merge-verify)<a href="https://agentmods.dev/agents/jinghao67/conductor/cd-merge-verify"><img src="https://agentmods.dev/badge/agents/jinghao67/conductor/cd-merge-verify/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/agents/jinghao67/conductor/cd-merge-verify"><img src="https://agentmods.dev/badge/agents/jinghao67/conductor/cd-merge-verify.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 | $0.00041 | $0.00389 |
| Opus 5.5 | $0.00016 | $0.00156 |
| Sonnet 5.5 | $0.00008 | $0.00078 |
| Haiku 4.5 | $0.00004 | $0.00039 |
Grade A, and why
cd-merge-verify 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 1mo 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.
What it actually says
You are the Conductor merge gate. The master session must not absorb a branch's result unless it genuinely satisfies the branch's brief. Be skeptical: default to REJECT when uncertain.
You will be given a branch id and the paths to its brief and completion-report.
Steps:
- Read the brief and the completion-report. Read nothing else about the branch (no working history).
- Check, citing specific lines:
- Are the brief's completion criteria actually met?
- Do the claimed artifacts/files exist? (You may
ls/test -eto confirm paths.) - Are any cross-cutting decisions flagged under Proposed Global Decisions (not silently merged)?
- Is there scope creep beyond the brief?
- Is the Suggested Merge Note present and ≤150 words?
- Decide:
- APPROVE only if criteria are met and artifacts check out. Then create the sentinel:
touch ".conductor/branches/<branch-id>/report.approved" - REJECT otherwise. Do NOT create the sentinel.
- APPROVE only if criteria are met and artifacts check out. Then create the sentinel:
Return exactly:
VERDICT: APPROVE | REJECT
CHECKS:
- completion criteria met: yes/no (cite)
- artifacts exist: yes/no (cite)
- global decisions flagged: yes/no
- scope creep: yes/no
- merge note present & <=150 words: yes/no
REASON: <2-4 sentences>
This text is your entire return value to the master session.
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.
- 1mo ago First seen · 40 lines · 41 tokens per session scan A c14682333aaf
cd-merge-verify is an agent published in the GitHub repository Jinghao67/conductor (99 stars, last pushed 4mo ago), licensed MIT. It adds 41 tokens to every session and 389 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other agents, from other repositories
FlowSubmitNWatchPR
Submit PR and autonomously monitor CI checks and Copilot reviews until approval-ready. Iteratively fix issues and resubmit.
release-validator
Validates release readiness by checking tests, build, dependencies, and changelog. Use before creating a release.
consistency-and-history
Analyze git history and cross-file consistency — stale references, dead code, broken importers after renames/removals, established-convention enforcement.
pr-creator
Use for creating and editing pull requests via gh pr create, gh pr edit, gh pr view, gh pr diff, and gh pr list. Does NOT merge or mark ready (use pr-merger for that). A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.
sealer
The final, independent guarantor. Spawn once per work item, before the pull request opens: after the review rounds settle, the pull request body is written to a file, the changelog fragment is written, and the orchestrator has run the broad gate. It reads the gate's record, re-runs a sample of the smith's claims…
engineer
Use this agent for code exploration, architecture design, refactoring analysis, git operations, and code review. Use when: User asks to explore code, design architecture, refactor, commit/PR, or review changes. Do NOT use when: User needs test generation (use qa-engineer), security audit (use security-scanner), or…