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 skills/danmcinerney/orchflows/orch-loopnpx skills add DanMcInerney/orchflows --skill orch-loopgit clone --depth 1 https://github.com/DanMcInerney/orchflowsWhat 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 | $0.00029 | $0.00512 |
| Opus 5 | $0.00015 | $0.00256 |
| Sonnet 5 | $0.00006 | $0.00102 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
orch-loop 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 3d 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
Require: a frozen goal; the body per rules/loops.md §9; a done-check naming its oracle and oracle_class per contracts/verdict.md; a bound; and the context packet the iterations carry — design it once via references/context-packet.md.
Each iteration: issue <id>.iter.NN through tickets.py new
(contracts/work-item.md,
Semantic assignment), promote it with tickets.py ready, and run that ticket
through orch-frontier, which owns its dispatch-v1 attempt and receipt; start
fresh from the frozen goal plus the worklog
tickets.py worklog renders; dispatch the body per
rules/delegation.md, carrying the context
packet in the iteration ticket's own ## Context so the committed dispatch
packet delivers it and no field travels beside the ticket;
adjudicate the return through orch-integrate; let the
done-check decide per the contract's class policy.
Exit complete on rules/loops.md §1's
done-check and stalled or limited per §5, plus blocked on an
unresolvable dependency and failed on an unrecoverable execution
error. Where a predecessor — a nested loop, or a cited earlier run —
closed limited, name that limitation and the evidence that decided it
in this run's own result, and carry it into the packet's failed-approaches
digest: §7 forbids promoting a limited exit into complete, and a
limitation nobody restates is one the next iteration re-walks.
Never: count an iteration's own claim as the done-check; end a judged-class run on iteration-time green; accept an iteration solely on its executor's claim — it takes one outside evidence path under rules/verification.md §7 before counting as progress, and where no such path is available the dispatch is refused.
Return: status, results by identity, final verification, iterations run, queued scope, and bounds spent.
What ships with it
1 file 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.
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.
- 3d ago First seen · 43 lines · 29 tokens per session scan A 71d6f7203c2c
orch-loop is a skill published in the GitHub repository DanMcInerney/orchflows (51 stars, last pushed 3d ago), licensed MIT. It adds 29 tokens to every session and 512 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…