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 megamen32/LastHumanCommit --skill improve-workflowgit clone --depth 1 https://github.com/megamen32/LastHumanCommitWrote 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/megamen32/lasthumancommit/improve-workflow)<a href="https://agentmods.dev/skills/megamen32/lasthumancommit/improve-workflow"><img src="https://agentmods.dev/badge/skills/megamen32/lasthumancommit/improve-workflow/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/megamen32/lasthumancommit/improve-workflow"><img src="https://agentmods.dev/badge/skills/megamen32/lasthumancommit/improve-workflow.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 | $0.00031 | $0.00871 |
| Opus 5.5 | $0.00012 | $0.00348 |
| Sonnet 5.5 | $0.00006 | $0.00174 |
| Haiku 4.5 | $0.00003 | $0.00087 |
Grade A, and why
improve-workflow 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Improve the factory, not just the journal
Mandatory at least every120 wall-clock minutes during unfinished work, and on user correction, substantial overrun, repeated route failure and cycle completion. Every maximum overrun requires a route decision. Overseer demands the accepted business result; a learning receipt never replaces it or justifies CONTINUE. The objective clock survives phase changes and compaction. Use the persistent lhc_time_guard checkpoint; notification is not completion. With no native hook, check manually at work boundaries; after idle periods check on resumption without background wakeups. Use also after a meaningful reusable signal, or for a selected factory-improvement task. A brief consideration is enough when there is no useful observation. Do not append four empty answers after every task.
Keep inspection within five minutes and choose at most one actionable correction. Compare cumulative cost and accepted user results before selecting it. Record observation, changed method, verification and next route in the existing task, then explicitly acknowledge the checkpoint. Evidence-backed no-change is valid when no improvement is indicated; repeated failure makes that excuse invalid. Do not reset the clock, start a new feature, fabricate evidence or create a new memory system to satisfy this rule. See common/protocols/SELF_IMPROVE.md for the bounded loop; Hermes uses its verified native learning owner at the same cadence.
Capture and place
For a deliberate shortcut with a real known ceiling, keep the ceiling and the
observable trigger for revisiting it beside the code (a short ponytail: comment)
or in the owning project's existing task. Reuse that record; do not build a
second debt database or run a mandatory whole-repo scan. On a relevant debt review,
summarize marked shortcuts as location, limit, revisit trigger; missing triggers
are actionable. Ordinary simple code needs no debt marker.
Record the observed episode, conditions and evidence. Include successful shortcuts, not only failures. Find an existing matching lesson before duplicating it. Classify the improvement at the right owner: project fact, user preference, reusable skill, mechanical script, model-routing hint, or genuinely changed role responsibility. A local mistake does not automatically justify a global rule.
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 Changed · +23 lines c0e037b59e05
- 1mo ago First seen · 55 lines · 31 tokens per session scan A d57bcb3f7db6
improve-workflow is a skill published in the GitHub repository megamen32/LastHumanCommit (2 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 871 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 2026-09-05.
Other skills, from other repositories
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…
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…
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
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…