Borrowing it
Nothing to install: this file belongs to okuzpe/midas-harness. 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/okuzpe/midas-harness/main/.agents/skills/midas-capture/SKILL.mdgit clone --depth 1 https://github.com/okuzpe/midas-harnessWrote 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/okuzpe/midas-harness/midas-capture)<a href="https://agentmods.dev/skills/okuzpe/midas-harness/midas-capture"><img src="https://agentmods.dev/badge/skills/okuzpe/midas-harness/midas-capture/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/okuzpe/midas-harness/midas-capture"><img src="https://agentmods.dev/badge/skills/okuzpe/midas-harness/midas-capture.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 | $0.00068 | $0.01765 |
| Opus 5 | $0.00034 | $0.00882 |
| Sonnet 5 | $0.00014 | $0.00353 |
| Haiku 4.5 | $0.00007 | $0.00177 |
Grade A, and why
midas-capture 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
midas-capture — Crystallize a recurring pattern into a rule / playbook / convention
Guard + state:
<paths.engine>/templates/skill-state-ritual.md(+AGENTS.md§ Safety / Path resolution).
Run only when the user explicitly invokes this command, or right after they confirm a captured-pattern proposal. Never write a rule/playbook/convention silently — the user says yes first.
When you ask for the same thing over and over, that preference should become part of the project's
standards instead of living in chat. This skill — and the always-on capture behaviour in AGENTS.md —
turns a recurring request or correction into the right codified artifact, so every later sprint and
Phase-8 audit honours it automatically. It writes to the visible project artifacts you review in git;
Midas has no hidden memory / runtime store.
When the agent proposes this on its own (the always-on loop)
Across any phase, if the user asks for the same thing ~2-3 times, or corrects you the same way repeatedly, pause and propose capturing it — recommend-don't-wall, never write silently:
"You've asked for X three times — want me to capture it as a rule so every sprint follows it?" On the user's OK, run the procedure below. On no, drop it (don't nag).
The rubric — which artifact? (this answers "rule or skill?")
| The recurring thing is… | Capture as | Where |
|---|---|---|
| a constraint / preference ("always use X", "never Y") a reviewer can pass/fail | rule (with a **CHECK:**) |
<paths.rules>/<slug>.md |
| a procedure done the project's way ("when I add an endpoint, do A→B→C") | playbook | {product}/playbooks/<verb-noun>.md |
| a prose preference that isn't a mechanical check | convention | {product}/conventions.md |
| (rarely) a genuinely new invokable engine command | a skill — almost never per-project | — |
Default to a rule when it's checkable, a playbook when it's a multi-step recipe. A per-project pattern is a rule/playbook/convention — Midas keeps new slash-commands at the engine level, not per project.
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 · 109 lines · 68 tokens per session scan A de218b422183
midas-capture is a skill published in the GitHub repository okuzpe/midas-harness (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 68 tokens to every session and 1,765 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 2026-08-31.
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…