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 skills add richfrem/agent-plugins-skills --skill orchestrating-agent-workgit clone --depth 1 https://github.com/richfrem/agent-plugins-skillsWrote 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/skills/richfrem/agent-plugins-skills/orchestrating-agent-work)<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/orchestrating-agent-work"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/orchestrating-agent-work/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/skills/richfrem/agent-plugins-skills/orchestrating-agent-work"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/orchestrating-agent-work.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 | $0.00115 | $0.01424 |
| Opus 5.5 | $0.00046 | $0.00570 |
| Sonnet 5.5 | $0.00023 | $0.00285 |
| Haiku 4.5 | $0.00012 | $0.00142 |
Grade A, and why
orchestrating-agent-work 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 yesterday.
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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrating Agent Work (orchestrating-agent-work)
Interactive front door: analyze the task, conduct diagnostic interview, select Graph vs. Loop, plan, execute, and verify.
Contents
Dependencies
Requires Python 3.8+ (standard library only).
Constraints
- Interactive Confirmation: Ask at most 3 questions (one per turn) for ambiguous dimensions; present structured choices with
Option A [Recommended]; human confirms or overrides selection before planning. - Topology First (Graph vs. Loop): Choose Graph (DAG) for distinct steps, parallel fan-out reads, or ordering barriers; choose Loop for iterative delegation.
- Trust but Verify: Never accept worker output without running automated test suites and auditing the git diff.
- Loop Isolation: Inner execution loops are strictly forbidden from running
gitwrite commands (commits and merges stay with caller). - Confinement & Redirection: Workspace mutations run in an isolated worktree; background CLI calls redirect stdin (
< /dev/null). - Human Gate Integrity: Graph runs with
--approval nonerequire an explicit human-approved manifest SHA; never self-sign manifests you wrote.
Quick Start
python3 scripts/select_strategy.py --out docs/plans/work-tasks/<task-id>/
python3 scripts/validate_manifest.py graph-manifest.json
python3 scripts/graph_runner.py graph-manifest.json --worktree .worktrees/task-<id> --approval prompt
Workflow
- Analyze: Ingest requirements, evaluate dependency structure, ordering barriers, concurrency, and risk (routing-and-closure.md).
- Interview & Select: Ask 1–3 structured questions; run
select_strategy.py; present Graph (DAG) vs Loop (Dual-Loop vs Swarm); confirm human agreement (strategy-selection.md). - Plan:
- Graph (DAG): Compile and validate
graph-manifest.json(graph-planning.md, topology-rules.md). - Dual-Loop: Author
handoffs/task_packet_<id>.mdwith atomic scope and "NO GIT" rule (strategy-dual-loop.md). - Parallel Swarm: Partition tasks into independent units; author
<id>.job.md(strategy-agent-swarm.md).
- Graph (DAG): Compile and validate
- Execute:
- Graph: Run state machine via
graph_runner.pywith worktree isolation and rollback (graph-execution.md). - Dual-Loop: Dispatch tactical coding worker into isolated worktree with stdin redirection (
< /dev/null). - Parallel Swarm: Run
swarm_run.pywith resume support.
- Graph: Run state machine via
- Verify & Close: Run test suites, audit diffs (
agent_orchestrator.py verify), and complete retrospective survey before completion.
What ships with it
43 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/templates/dual-loop-meta-tasks.md 1.6 KB
- assets/templates/loop_retrospective_template.md 1.5 KB
- assets/templates/red_team_briefing_template.md 747 B
- assets/templates/scratchpad-template.md 991 B
- assets/templates/strategy-packet-template.md 1.2 KB
- assets/templates/workflow-retrospective-template.md 1.3 KB
- evals/evals.json 7.0 KB
- references/acceptance-criteria.md 6.8 KB
- references/cheapest_models.json 845 B
- references/cheapest_models.md 1.1 KB
- references/cli-agent-executor.md 3.5 KB
- references/delegated-dag-refactoring-playbook.md 5.5 KB
- references/diagrams/agent_swarm.mmd 1.8 KB
- references/diagrams/dual_loop_architecture.mmd 1.4 KB
- references/diagrams/graph_execution_state_machine.mmd 823 B
- references/diagrams/graph-planner-flow.mmd 540 B
- references/diagrams/orchestrating_agent_work_architecture.mmd 4.5 KB
- references/fallback-tree.md 9.7 KB
- references/graph-execution.md 4.1 KB
- references/graph-manifest-schema.json 7.0 KB
- references/graph-planning.md 3.0 KB
- references/PATTERN_GUIDE.md 6.2 KB
- references/patterns.json 2.0 KB
- references/post_run_survey.md 1.4 KB
- references/routing-and-closure.md 2.2 KB
- references/strategy-agent-swarm.md 2.1 KB
- references/strategy-dual-loop.md 1.6 KB
- references/strategy-red-team-review.md 2.0 KB
- references/strategy-selection.md 3.8 KB
- references/topology-rules.md 6.0 KB
- scripts/agent_orchestrator.py 7.6 KB runs code
- scripts/graph_runner.py 36 KB runs code
- scripts/select_strategy.py 13 KB runs code
- scripts/swarm_run.py 28 KB runs code
- scripts/validate_manifest.py 20 KB runs code
- tests/test_graph_fixes.py 13 KB runs code
- tests/test_graph_runner.py 30 KB runs code
- tests/test_isolation.py 3.5 KB runs code
- tests/test_loop_strategies.py 7.7 KB runs code
- tests/test_select_strategy.py 7.8 KB runs code
- tests/test_swarm_run_models.py 3.1 KB runs code
- tests/test_swarm_run.py 9.4 KB runs code
- tests/test_validate_manifest.py 18 KB runs code
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.
- yesterday Changed f72b087d3c4e
- 2d ago First seen · 81 lines · 115 tokens per session scan A ed30c5963006
orchestrating-agent-work is a skill published in the GitHub repository richfrem/agent-plugins-skills (7 stars, last pushed 2d ago), licensed MIT. It adds 115 tokens to every session and 1,424 once invoked, about $0.0005 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 2026-10-24.
Other skills, from other repositories
autoprompt
Run explicitly requested Autoprompt v2 work through the private controller. Ordinary coding and review requests do not activate this skill.
autoprompt
Run explicitly requested Autoprompt v2 work through the private controller. Ordinary coding and review requests do not activate this skill.
ap-depth-prober
Report the compatibility redirect to ap-worker; this retired role cannot perform new work.
ap-fresh-verifier
Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.
triage
Triage a GitHub repository's open issues by finding exact duplicates, rejecting evidenceably off-base requests, requesting concrete clarification, applying only existing labels, and opening a linked root-cause issue when multiple reports share one underlying invariant failure. Use when a maintainer asks to triage…
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…