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 sjarmak/coding-agent-workflows --skill ruling-capturegit clone --depth 1 https://github.com/sjarmak/coding-agent-workflowsWrote 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/sjarmak/coding-agent-workflows/ruling-capture)<a href="https://agentmods.dev/skills/sjarmak/coding-agent-workflows/ruling-capture"><img src="https://agentmods.dev/badge/skills/sjarmak/coding-agent-workflows/ruling-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/sjarmak/coding-agent-workflows/ruling-capture"><img src="https://agentmods.dev/badge/skills/sjarmak/coding-agent-workflows/ruling-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 | $0.00117 | $0.01247 |
| Opus 5.5 | $0.00047 | $0.00499 |
| Sonnet 5.5 | $0.00023 | $0.00249 |
| Haiku 4.5 | $0.00012 | $0.00125 |
Grade A, and why
ruling-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 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ruling Capture
A user says "always expand a delete command before running it" or "route that kind of review to a different model" or "stop asking, just do it and tell me after." That is a ruling: a standing decision meant to bind every future session, issued in conversation and recorded nowhere. When the session ends it is gone, and the next session cheerfully does the thing it was told not to.
A ruling is durable only when a future session can find and apply it without access to the conversation that produced it.
How this differs from the two nearby skills
failure-mode-capture starts from an incident and requires a concrete
consequence. Its own text says that a rule without one "is a style preference,
and belongs in the bundle or a code review, not here." Many rulings are exactly
that: a preference, a priority call, a scope boundary, a judgment about how the
user wants to work. Real, binding, and outside that skill's stated scope.
context-layering says where a fact belongs and sets the ceiling on
AGENTS.md. It does not say how a ruling gets out of the conversation and into
a file. This skill is that procedure, for the specific case where the source is
the user talking rather than a bug.
Rule of thumb: a bug taught you something, use failure-mode-capture; a person
told you something, use this.
Where a ruling goes
Into the tracked document that owns its subject. That might be a conventions
file, an architecture decision record, a runbook, or an area's COMPASS.md.
Create a focused document when none owns the subject yet.
The main instructions file gets a one-line pointer and nothing more: what the rule is about, and the path to the document holding it. See TEMPLATE-pointer.md for the line and TEMPLATE-ruling-doc.md for the document.
Putting the full text inline because that file is always loaded charges every
unrelated session for it, forever. That is how an instructions file grows past
the ceiling context-layering sets.
What ships with it
4 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.
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 · 108 lines · 117 tokens per session scan A 5b373ae72597
ruling-capture is a skill published in the GitHub repository sjarmak/coding-agent-workflows (7 stars, last pushed 20d ago), licensed MIT. It adds 117 tokens to every session and 1,247 once invoked, about $0.0005 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 2026-09-16.
Other skills, from other repositories
planning-with-files
Persistent file-based planning for multi-step AI-agent work. Keeps taskplan.md, findings.md, and progress.md on disk; lifecycle hooks inject selected project planning context. Automatic recovery reads project planning files only. Explicit session-catchup.py --metadata reads same-project local agent session records and…
bopomofo-rescue
A text-recovery tool for Taiwanese Bopomofo, also called Zhuyin, keyboard mistakes. It converts letter-and-number sequences typed with the wrong input mode back into likely Chinese text.
ctx-purge
Purge the context-mode knowledge base. Permanently deletes all indexed content and resets session stats. This is destructive and cannot be undone. Trigger: /context-mode:ctx-purge.
context-window-engineer
Expert guide for engineering and optimizing ultra-large context windows (2M+ tokens) across Gemini 4 Pro, Claude 5.5, and GPT Astra 6 — context partitioning, retrieval-augmented context injection, sliding window strategies, and cost-aware token budgeting / Panduan ahli rekayasa dan optimasi context window ultra-besar…
forgetful-procedures
Store and find procedural knowledge — reusable step-by-step how-tos — in Forgetful's skill store. Use when a workflow worth repeating gets worked out, when the user asks how something is done here, or when importing or exporting SKILL.md files. Litmus: a procedure someone follows is a skill; a fact someone recalls is…
memory-md-management
Provides comprehensive memory file management capabilities including auditing, quality assessment, and targeted improvements for files such as CLAUDE.md. Use when user asks to check, audit, update, improve, fix, maintain, or validate project memory files. Also triggers for "project memory optimization", "CLAUDE.md…