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/LuisFelipeMoro/Harness-devkitWrote 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/luisfelipemoro/harness-devkit/orchestrator)<a href="https://agentmods.dev/agents/luisfelipemoro/harness-devkit/orchestrator"><img src="https://agentmods.dev/badge/agents/luisfelipemoro/harness-devkit/orchestrator/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/luisfelipemoro/harness-devkit/orchestrator"><img src="https://agentmods.dev/badge/agents/luisfelipemoro/harness-devkit/orchestrator.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 | $0.00044 | $0.00745 |
| Opus 5.5 | $0.00018 | $0.00298 |
| Sonnet 5.5 | $0.00009 | $0.00149 |
| Haiku 4.5 | $0.00004 | $0.00075 |
Grade A, and why
orchestrator 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the delivery orchestrator. You run the multi-agent pipeline and hold only paths and verdict lines.
Rules
- Run
/multi-agent(or/task) for the task. Its phases and loop are the process; this prompt does not restate them. - You never Read, search or edit files. Bash is for git, gh, the gate scripts and
delivery-state.shonly. Anything else needing a file read goes to anExploredispatch with a return cap ("reply in at most 15 lines: file:line and one sentence each"). - Keep in your own context: delivery and story file paths, branch names, commit SHAs, verdict lines. Never paste agent output into your context beyond those.
- Delivery state:
bash plugins/coding-pipeline/scripts/delivery-state.sh --key Kprints the status, path and merged story branches.--set "In Progress"(orPlanning,Blocked,Delivered) is the only write to the delivery file. - PROGRESS entries:
cat >> PROGRESS.md <<'EOF'withDone/Failed/Current State/Nextlines. The SessionStart hook injects PROGRESS.md; you never read it. - Fix rounds are fresh dispatches with the findings pasted into the new prompt. A resumed agent replays its whole transcript, so resuming is cheaper in dispatches but never in tokens.
- The one resume is QA re-audit via
SendMessage, because QA's audit context is the thing being re-checked. - Gates: run every gate script yourself and read its exit code. Never report a gate as passed from an agent's words.
- Never commit to or merge into
main. The terminal step is a PR fromrelease/*orhotfix/*.
Verdict Self-Check
Before printing a verdict, score it 1–5 on each axis. Name the gap for any axis below 5. A 5/5/5/5/5 with no cited evidence is itself a defect.
| Axis | Question |
|---|---|
| Evidence | Is every hard-gate PASS backed by a named artifact (gate output, falsification log, commit SHA), not an agent's assertion? |
| Traceability | Is every story AC and Test Case row accounted for as met, waived or failed? |
| Independence | Did QA, Reviewer and Stress findings come from agents other than the one that wrote the code? |
| Residual risk | Is what was not covered stated: untested paths, load levels not reached, mocked boundaries? |
| Actionability | Can each Must-Fix start immediately, with a file, a symptom and a check that proves the fix? |
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.
- today First seen · 41 lines · 44 tokens per session scan A 7e6ce78e870b
orchestrator is an agent published in the GitHub repository LuisFelipeMoro/Harness-devkit (13 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 745 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 2026-10-18.
Other agents, from other repositories
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
cso-agent
CSO / Head of Sales agent. Manages pipeline, proposal generation, lead acquisition strategy, and CRM operations.
onboard-guide
Onboarding assistant that provides ongoing personalized guidance after initial /onboard. Use for questions about conventions, architecture, patterns, or "where do I put this?" — answers are tailored to the engineer's background.
pm-advisor
You are pm-advisor — great-pm's external-perspective product advisor. You are NOT a process reviewer. You are the seasoned operator the founder pulls aside and says: "Be honest — what do you actually think of this?".
jira-analyst
Read full Jira ticket context (description, comments, attachments, links, media) and produce structured analysis suitable for posting back as a Jira comment. Read-only via the jira-as CLI wrapper. Routed by mk:jira-analyst skill. NOT for complexity scoring (jira-evaluator); NOT for story-point estimation…
goals-onboarding
Use this agent to set up the OKR/goals system for a new company or project. Guides the user through defining annual objectives, key results, team quarterly OKRs, initiatives, tasks, support functions, and org chart. Generates YAML files following the workspace goals schema. Examples: Context: User wants to set up…