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 sorah/config --skill codinggit clone --depth 1 https://github.com/sorah/configWrote 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/sorah/config/coding)<a href="https://agentmods.dev/skills/sorah/config/coding"><img src="https://agentmods.dev/badge/skills/sorah/config/coding/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/sorah/config/coding"><img src="https://agentmods.dev/badge/skills/sorah/config/coding.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 | $0.00042 | $0.01123 |
| Opus 5.5 | $0.00017 | $0.00449 |
| Sonnet 5.5 | $0.00008 | $0.00225 |
| Haiku 4.5 | $0.00004 | $0.00112 |
Grade A, and why
coding 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 yesterday.
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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
General Coding Guidelines
Language-agnostic coding conventions applicable across all projects. Project-specific conventions (CLAUDE.md, style guides) always take priority over this guidance.
Code Quality
- Do not leave empty lines containing only whitespace
- Write clean, readable code that follows the language's established conventions
- Use consistent indentation and formatting
Code Comments
Comments must not repeat what the code already expresses. Use comments to explain why something is done, or to record context that cannot be recovered from the code itself.
Three rules govern everything below.
Write for a stranger reading the file, not a reviewer reading the diff. The reader has never seen the pull request, the spec, the ticket, the review discussion, or the previous version of the code. A comment that only makes sense with that context is noise to everyone else.
Keep them short. Default to a single line. Use two or three only when one genuinely cannot carry the constraint. This applies to doc comments too: a class or method doc comment states what the thing is and what it guarantees, in a sentence or two. It is not a design document.
Avoid narrative. A comment states a fact. It does not build to a point, weigh alternatives, or qualify itself. Punctuation is a reliable tell: reaching for an em dash, a semicolon, or a colon that introduces an explanation is the signal to stop and cut, not to keep writing. So is a second sentence opening with "But", "So", "Note that", or "In practice".
When to comment:
- To explain why a non-obvious approach or workaround was chosen
- To clarify intent when the code could be misread or misunderstood
- To record an external constraint (protocol, spec, upstream bug, API quirk) the code must satisfy
- To document an assumption, edge case, or limitation a reader would otherwise have to rediscover
When not to comment:
- Do not narrate what the code is doing, the code already says that
- Do not duplicate function or variable names in plain English
- Do not leave stale comments that contradict the code
- Do not reference removed or obsolete code paths
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.
- yesterday First seen · 81 lines · 42 tokens per session scan A 043d78894c51
coding is a skill published in the GitHub repository sorah/config (31 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 1,123 once invoked, about $0.0002 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 2026-10-17.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…