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.
npx agentmods add commands/emtcmca/promptsmith/orchestrategit clone --depth 1 https://github.com/emtcmca/promptsmithWhat 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 | $0.00043 | $0.00763 |
| Opus 5 | $0.00022 | $0.00381 |
| Sonnet 5 | $0.00009 | $0.00153 |
| Haiku 4.5 | $0.00004 | $0.00076 |
Grade A, and why
orchestrate 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run the promptsmith coordinator on a request that spans more than one specialist. Output is a
single synthesized deliverable plus the decomposition, seam owners, resolved conflicts, and any
coverage gaps. Layer 2 — this dispatches live subagents, so it needs a host that can spawn
them (Claude Code). For a single-domain task, use /promptsmith:sharpen instead.
Step 1 — Load the engine
Read ${CLAUDE_PLUGIN_ROOT}/skills/orchestration/SKILL.md in full. It defines the coordinator
pipeline. (That engine itself loads the Layer 1 prompt-engineering skill in its Step 1.)
Paths.
${CLAUDE_PLUGIN_ROOT}is this plugin's install directory, substituted automatically — never a literal folder in the user's project. If promptsmith was installed standalone (README Option B, no plugin root), read from~/.claude/instead:~/.claude/skills/…,~/.claude/promptsmith-templates/,~/.claude/promptsmith-lenses/,~/.claude/promptsmith-agents/. Never resolve these against the user's working directory.
Step 2 — Parse arguments
Parse $ARGUMENTS:
--dry— stop after the decomposition + plan (Step 5). Show slices, slice→agent map, seams, conflicts, coverage gaps, and fan-out size. Do not dispatch. Useful for inspecting routing.--gate— always pause for approval before fan-out (override the smart threshold).--no-gate— never pause for approval; run autonomously through dispatch + synthesis. Does not waive the intent gate (Step 0) or the adversarial-verify gate (Step 6.5) — those always apply.- (default) — smart threshold: auto-run small/low-risk plans (≤ 3 agents, nothing irreversible); gate larger or risky fan-outs. See engine Step 5.
- Everything else = the multi-domain request to coordinate.
If the request is empty, ask what to coordinate and stop.
Step 3 — Run the pipeline
Execute the orchestration pipeline (engine Steps 0–8):
0. Gate — if it's really single-domain, fall back to /promptsmith:sharpen or the one agent.
- Sharpen the query (Layer 1 engine).
- Decompose into non-overlapping slices.
- Route slices to gallery agents; log uncovered slices as coverage gaps.
- Identify seams + conflicts; assign owners; resolve or flag conflicts.
- Approval gate (unless
--no-gate). - Dispatch each slice's agent as a subagent (parallel where independent).
- Assemble + curate into one coherent deliverable.
- Report.
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.
- 2d ago First seen · 56 lines · 43 tokens per session scan A ee537f683f92
orchestrate is a command published in the GitHub repository emtcmca/promptsmith (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 763 once invoked, about $0.0002 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 2026-08-31.
Other commands, from other repositories
mach12:pr-review-assessment
Independently assess each finding from a PR review and classify it.
mach12:issue-review
Read a GitHub issue and all comments, review the implementation plan, and present findings.
mach12:issue-plan
Read a GitHub issue, analyze the codebase, and create a staged implementation plan.
mach12:pr-pre-merge
Run the pre-merge checklist - branch freshness, docs, version, CHANGELOG, tests, CI.
mach12:pr-review-fix
Fix specific issues identified in a PR review.
mach12:issue-implement
Implement a specific stage of an issue's implementation plan.