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 dominno/squid --skill squid-pipelinegit clone --depth 1 https://github.com/dominno/squidWrote 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/dominno/squid/squid-pipeline)<a href="https://agentmods.dev/skills/dominno/squid/squid-pipeline"><img src="https://agentmods.dev/badge/skills/dominno/squid/squid-pipeline.svg" alt="Measured on agentmods" 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 | $0.00079 | $0.05681 |
| Opus 5 | $0.00039 | $0.02840 |
| Sonnet 5 | $0.00016 | $0.01136 |
| Haiku 4.5 | $0.00008 | $0.00568 |
Grade A, and why
squid-pipeline 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 8d 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 — 525 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Required Reading — Reference Files
This skill includes reference docs and working examples. You MUST read the relevant files before generating pipelines or tests. SKILL.md alone is not sufficient — the references contain critical syntax details.
BEFORE creating or modifying any pipeline, read:
references/step-types.md— Full config for every step type (run, spawn, gate, parallel, loop, branch, transform, pipeline). Contains exact field names, types, and valid values.references/patterns.md— Validated workflow patterns with complete YAML examples. Use these as templates.
BEFORE creating or modifying any test file, read:
references/testing.md— Full test file schema, mock syntax, assertion types, mode behaviors. Contains exact valid field names and values.
BEFORE writing a pipeline that matches an example pattern, read the matching example:
examples/simple-deploy.yaml+examples/simple-deploy.test.yaml— Basic pipeline with testsexamples/multi-agent-dev.yaml— Multi-agent with parallel branchesexamples/iterative-refinement.yaml— Restart loop patternexamples/advanced-gates.yaml— Structured gate inputexamples/orchestrator.yaml— Sub-pipeline composition
All paths are relative to this skill directory.
Install
If Squid is not installed, install it first:
git clone https://github.com/dominno/squid.git
cd squid
npm install
npm run build
Then use directly:
npx squid run pipeline.yaml
npx squid test
npx squid validate pipeline.yaml
npx squid viz pipeline.yaml
npx squid init --template basic --name my-pipeline
Or link globally:
npm link
squid run pipeline.yaml
Requires Node.js 20+.
Mandatory Rules
These rules are NON-NEGOTIABLE. Every pipeline you generate MUST follow all of them. Violations are bugs.
R1: Gate before side effects
Any step that modifies external state (git push, API POST, deploy, file write to shared storage, PR creation, sending messages) MUST be preceded by a type: gate step. The side-effect step MUST have when: $gate.approved in its condition.
What ships with it
27 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.
- examples/advanced-gates.yaml 3.0 KB
- examples/e2e/e2e-claude-code.yaml 856 B
- examples/e2e/e2e-code-review-loop.test.yaml 407 B
- examples/e2e/e2e-code-review-loop.yaml 2.9 KB
- examples/e2e/e2e-error-recovery.yaml 1.8 KB
- examples/e2e/e2e-gate-resume.yaml 1.4 KB
- examples/e2e/e2e-loop-items.yaml 1.4 KB
- examples/e2e/e2e-mixed-adapters.yaml 1.3 KB
- examples/e2e/e2e-openclaw.yaml 853 B
- examples/e2e/e2e-parallel-agents.yaml 1.8 KB
- examples/e2e/e2e-sub-pipeline-child.yaml 967 B
- examples/e2e/e2e-sub-pipeline.yaml 1.1 KB
- examples/iterative-refinement.yaml 3.1 KB
- examples/lobster-migration.yaml 3.2 KB
- examples/multi-agent-dev.yaml 6.6 KB
- examples/observability.yaml 2.9 KB
- examples/orchestrator.yaml 3.7 KB
- examples/simple-deploy.test.yaml 2.0 KB
- examples/simple-deploy.yaml 1.1 KB
- examples/sub-build.test.yaml 1.5 KB
- examples/sub-build.yaml 1.1 KB
- examples/sub-deploy.yaml 1.5 KB
- examples/sub-test.yaml 1.4 KB
- examples/video-pipeline.yaml 5.0 KB
- references/patterns.md 5.0 KB
- references/step-types.md 7.5 KB
- references/testing.md 4.8 KB
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.
- 8d ago First seen · 525 lines · 79 tokens per session scan A 26c123f9b156
squid-pipeline is a skill published in the GitHub repository dominno/squid (11 stars, last pushed 5mo ago), licensed MIT. It adds 79 tokens to every session and 5,681 once invoked, about $0.0004 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.
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…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…