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 signalridge/slipway --skill decomposegit clone --depth 1 https://github.com/signalridge/slipwayWrote 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/signalridge/slipway/decompose)<a href="https://agentmods.dev/skills/signalridge/slipway/decompose"><img src="https://agentmods.dev/badge/skills/signalridge/slipway/decompose/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/signalridge/slipway/decompose"><img src="https://agentmods.dev/badge/skills/signalridge/slipway/decompose.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 11 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 33 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00020 | $0.01539 |
| Opus 5.5 | $0.00008 | $0.00616 |
| Sonnet 5.5 | $0.00004 | $0.00308 |
| Haiku 4.5 | $0.00002 | $0.00154 |
Grade A, and why
slipway-decompose 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 1mo 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slipway Decompose
Use this capability only when the user explicitly asks to decompose a marker-valid Objective or amend its open child Changes. Do not implement the resulting work.
Read the current Objective, repository facts, existing sub-issues and dependencies, provider node identities, and current Issue revisions. Only the exact first marker <!-- slipway-level: objective/v1 --> and valid Objective body content determine decomposition eligibility. Inspect title and labels, but missing or conflicting labels never block decomposition: report projection drift as a warning. Repairing title or labels is a separate, explicitly confirmed external write and must not be bundled into decomposition merely to make the Objective appear valid. Treat the Objective as planning input, never as runtime inheritance.
Produce coherent tracer-bullet Changes that each have one observable result, can be independently delivered, verified, rolled back, leave the repository meaningful and safe, and roughly fit one fresh Agent context. Split only independently deliverable outcomes; keep non-deliverable implementation steps as checklists. Materialize every applicable Objective requirement and shared constraint into each child's manifest-addressed chapter comments. Each child starts with <!-- slipway-level: change/v2 -->, has exactly one level:change and exactly one of kind:feature|kind:bug|kind:refactor|kind:maintenance|kind:research|kind:docs, and its manifest covers the required Outcome, Requirements, Acceptance examples, Constraints, and Non-goals roles; no child may depend on rereading its parent or unreferenced discussion. Keep Kind independent of the parent. Research delivers an evidence-backed conclusion and leaves later code to another Change. Pure refactors state preserved behavior and a measurable internal outcome; wide refactors use expand, independently deliverable migration batches, then contract.
Show a numbered decomposition before writing: every Change's complete effective Requirements, delivery result, acceptance examples, blockers, exact labels, parent relation, publication item UUID, every pre-existing mutable target's provider identity and observed revision, expected parent Requirements revision, and any missing-label creation with exact attributes. Use GitHub native sub-issues for Objective-to-Change and native blocked-by dependencies for Change-to-Change. Keep one hierarchy level. A plan may reach exactly 100 children, exactly 50 blocking dependencies, and exactly 50 blocked-by dependencies per Issue; treat blocking and blocked-by as independent directions. Stop and report only when the approved write would exceed one of those limits, and recommend how to repartition the Objective into smaller coherent Objectives or publication operations. Never convert overflow to prose or a gate.
GitHub closed status does not prove that a blocker Change was actually delivered. The planning frontier may use that state as a signal, but it must remain advisory rather than locked; the user retains authority to override it.
{{ template "source-bundle" . }}
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.
- 1mo ago First seen · 54 lines · 20 tokens per session scan A 57db61bfefee
slipway-decompose is a skill published in the GitHub repository signalridge/slipway (23 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 20 tokens to every session and 1,539 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
repo-hygiene
Use when the scheduled repo-hygiene workflow runs from GitHub Actions (or an operator dry-run) to scan the repository for small, certain docs/test/code hygiene issues and fix them as one batched branch.
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
requirements-writer
Use when converting PM intake into a slice SPEC.md with observable acceptance outcomes, explicit scope, and advisory sibling build dependencies.
refocusing
Use when a long-running agent may have lost the product outcome, when context was compacted, when work has crossed a major boundary, or when a fresh path-based trace is needed before the next consequential action. Not for fresh-session orientation, waking an idle seat, or checkpoints.
orchestration-team
Use when coordinating assignments, selected review boundaries, or blocked work across a rig.
oversight-team
Use when you are a seat on the oversight pod (a standing monitor-mode rig that keeps OTHER rigs healthy), configuring or running the drift detectors, or choosing whether to intervene vs escalate. Covers the pull-not-poll posture, the v0 detectors (premature-park, process-drift, off-task, token-burn), the intervention…