Borrowing it
Nothing to install: this file belongs to LionelHuanSi/awesome-ai-agent-skills. 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/LionelHuanSi/awesome-ai-agent-skills/main/.agents/skills/exact-coding/SKILL.mdgit clone --depth 1 https://github.com/LionelHuanSi/awesome-ai-agent-skillsWrote 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/lionelhuansi/awesome-ai-agent-skills/exact-coding)<a href="https://agentmods.dev/skills/lionelhuansi/awesome-ai-agent-skills/exact-coding"><img src="https://agentmods.dev/badge/skills/lionelhuansi/awesome-ai-agent-skills/exact-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/lionelhuansi/awesome-ai-agent-skills/exact-coding"><img src="https://agentmods.dev/badge/skills/lionelhuansi/awesome-ai-agent-skills/exact-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 | $0.00041 | $0.00534 |
| Opus 5.5 | $0.00016 | $0.00214 |
| Sonnet 5.5 | $0.00008 | $0.00107 |
| Haiku 4.5 | $0.00004 | $0.00053 |
Grade A, and why
exact-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 2mo 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EXACT Coding & AI Code Review Skill (Enhanced with Claude Code Patterns)
Sourced from steveyo/andrej-karpathy-skills, Claude Code Autonomous Execution Protocols, and 3-Layer AI Code Review standards.
Karpathy's 4 Core Pillars
1. Think Before Coding
- Never guess code logic, schemas, or file paths without inspecting source files first.
- If requirements have ambiguities or multiple possible interpretations, explicitly list trade-offs before implementation.
2. Simplicity First
- Minimum code to solve the problem. Zero speculative code.
- No unused abstractions, unnecessary configurability, or complex wrapper functions.
- If a 200-line implementation can be simplified to 50 lines, rewrite it.
3. Surgical Changes
- Touch only the lines required for the requested feature or fix.
- Do NOT reformat adjacent unrelated code, reorder imports, or touch working comments.
- Clean up orphan variables/imports created by your edits, but leave pre-existing dead code untouched.
4. Goal-Driven Execution
- Every task must have a verifiable outcome (passing unit test, clean build, matching endpoint payload).
- Run verification tools and inspect logs before declaring success.
Claude Code Autonomous Protocols
1. Autonomous Self-Healing Debug Loop
When a build, test, or execution command fails:
- Log Extraction: Read the un-truncated error log immediately. Do NOT guess the cause blindly.
- Root Cause Analysis: Identify the broken contract or failing assertion.
- Surgical Patch: Apply a targeted code fix without altering unrelated functions.
- Re-Verification: Re-run the exact failing test/command. Repeat until 100% SUCCESS is achieved before ending turn.
2. Strict Scope Guard
- Maintain an explicit whitelist of files authorized for modification.
3. Visual QA & Browser Verification
- For UI or web endpoint changes, launch a Browser subagent (
browser_subagent) to verify layout, screenshots, and logs.
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.
- 2mo ago First seen · 53 lines · 41 tokens per session scan A 25a9800ad515
exact-coding is a skill published in the GitHub repository LionelHuanSi/awesome-ai-agent-skills (3 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 534 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 2026-08-31.
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"…
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…
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…