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 HiAgencia/hi-claude --skill work-protocolgit clone --depth 1 https://github.com/HiAgencia/hi-claudeWrote 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/hiagencia/hi-claude/work-protocol)<a href="https://agentmods.dev/skills/hiagencia/hi-claude/work-protocol"><img src="https://agentmods.dev/badge/skills/hiagencia/hi-claude/work-protocol/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/hiagencia/hi-claude/work-protocol"><img src="https://agentmods.dev/badge/skills/hiagencia/hi-claude/work-protocol.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 | $0.00305 | $0.02855 |
| Opus 5 | $0.00152 | $0.01427 |
| Sonnet 5 | $0.00061 | $0.00571 |
| Haiku 4.5 | $0.00030 | $0.00285 |
Grade A, and why
work-protocol 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 9d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work protocol (hi-claude)
How it gets WRITTEN
This skill carries the WRITING axis of the method. The principles themselves are defined in the Constitution, which every session already carries — here is how a violation is spotted in a draft.
| Spotted in a draft | Rewrite it as |
|---|---|
| a door closed on a future session — any of the shapes the Constitution forbids | the state OBSERVED, plus the condition that would reopen it |
| a cause or an intent asserted without evidence, or a grade where a measurement belongs | the fact and its evidence, no verdict of value |
| something that expires — a date, a state, a moment | the invariant behind it, or it goes unwritten |
| a line already written that stopped being true, or that no future session would open | delete it — see PRUNED below; git keeps what leaves |
- A measured result is a DATUM with its N and its method, REOPENABLE — never a closed verdict. What was measured and not adopted is recorded with the evidence that closed it, and with the condition that would reopen it.
- Documentation does NOT accumulate history. Each line is judged by whether it serves a FUTURE session. What describes what already happened — an executed plan, a "✅ done", the chronicle of what changed and why — is DELETED. Its design lives in the work itself and in the commits.
- Pending vs context: a pending register (
ROADMAP.md) carries only what is missing and how it relates to other pendings; when an item closes it is DELETED, not marked done. What is structural — architecture, doctrine, contracts — is not a pending: it lives in the context documents.
How it gets COMMUNICATED
- This is read by an AI: imperative, no narrative, no filler, no war stories. Metric before prose.
- Explain only what changes a decision. Zero tokens on what does not.
- Do not write what is visible by looking at the repo (the file tree, module names, what a docstring already says). The tokens go to GOTCHAS: what bites and cannot be deduced.
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.
- 9d ago First seen · 171 lines · 305 tokens per session scan A 22bc68cfc59e
work-protocol is a skill published in the GitHub repository HiAgencia/hi-claude (2 stars, last pushed 19d ago), licensed MIT. It adds 305 tokens to every session and 2,855 once invoked, about $0.0015 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 2026-08-31.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
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…