Borrowing it
Nothing to install: this file belongs to acartine/foolery. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/acartine/foolery/main/.agents/skills/knots-plan-orchestrator/SKILL.mdgit clone --depth 1 https://github.com/acartine/fooleryWrote 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/acartine/foolery/knots-plan-orchestrator)<a href="https://agentmods.dev/skills/acartine/foolery/knots-plan-orchestrator"><img src="https://agentmods.dev/badge/skills/acartine/foolery/knots-plan-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/skills/acartine/foolery/knots-plan-orchestrator"><img src="https://agentmods.dev/badge/skills/acartine/foolery/knots-plan-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00050 | $0.00916 |
| Opus 5 | $0.00025 | $0.00458 |
| Sonnet 5 | $0.00010 | $0.00183 |
| Haiku 4.5 | $0.00005 | $0.00092 |
Grade A, and why
knots-plan-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 10d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knots Plan Orchestrator
Agent identity
Create or receive a lease for the orchestrator before reading or advancing the plan:
kno lease create --nickname "<session-name>"
Use the orchestrator lease for plan-level notes, handoff capsules, and plan
state transitions. Each launched worker must receive or create its own lease
and claim its assigned knot with --lease <lease-id> so metadata authorship
comes from the bound lease instead of [unknown <date>].
Do not copy legacy --*-agentname/model/version identity flags from telemetry
or command history. They are deprecated and ignored by current kno.
Load the plan
kno show <plan-id> --json
Parse the execution_plan field from the JSON output. The plan contains an
ordered waves array, each wave contains an ordered steps array, and each
step contains a knot_ids array representing the concurrent work set.
- If you are working inside a git worktree, run Knots commands as
kno -C <path_to_repo> ...because Knots is installed for the repo root, not the worktree path.
Orchestration protocol
Process the plan using these sequencing rules:
- Waves are sequential. Process waves in ascending
wave_indexorder. Do not start wave N+1 until every knot in wave N has reached a terminal or passive waiting state. - Steps within a wave are sequential. Process steps in ascending
step_indexorder. Do not start step N+1 until every knot in step N has reached a terminal or passive waiting state. - Knots within a step are concurrent. Launch every knot in one step at the same time. Follow your own protocol for launching and managing coding agents — this skill does not prescribe how agents are spawned.
Process each step
For each step in the current wave:
- Read the
knot_idsarray from the step. - For each knot id, check its current state:
kno show <knot-id> --json
- Skip knots already in a terminal state (
SHIPPED) or a passive waiting state (BLOCKED,DEFERRED). - Launch all remaining knots concurrently. Delegate to your agent-launching protocol and pass each worker its lease id; do not inline the execution of a knot inside the orchestrator.
- Wait for every launched knot to reach
SHIPPED,BLOCKED, orDEFERREDbefore moving to the next step.
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.
- 10d ago First seen · 116 lines · 50 tokens per session scan A 6e6215503586
knots-plan-orchestrator is a skill published in the GitHub repository acartine/foolery (54 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 916 once invoked, about $0.0003 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
flow-state
Use when a Flow request reads, mutates, reconciles, completes, archives, or recovers Markdown lifecycle state and transaction journals.
flow-execution
Use when implementing Flow tasks from local task files under .agents/bundles/specs/ /tasks/, claiming ready work, applying the declared verification strategy, recording task notes, committing, and updating task file state.
flow-completion
Use when reviewing, finishing, archiving, reverting, validating, documenting, or cleaning up Flow work after implementation or phase completion.
flow-sync-status
Use when reconciling Flow task truth into a spec, displaying status queues, refreshing project context, or checking bundle state anomalies.
work-beads
Work the project's Beads task queue end-to-end - claim a bead, build in an isolated worktree, verify, review, merge, close, report. Use when the user says "/work-beads", "/work-beads 5", "work the next N beads", "work on ", "pick up some open tasks", or asks to work the backlog. Applies to every coding agent (Claude…
file-todos
Manage file-based todos in todos/ directory. Use when creating, triaging, or tracking todos and integrating them with code review.