Borrowing it
Nothing to install: this file belongs to SecondLifes/code-intel. 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/SecondLifes/code-intel/main/.agents/skills/rad-code-fix/SKILL.mdgit clone --depth 1 https://github.com/SecondLifes/code-intelWrote 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/secondlifes/code-intel/rad-code-fix)<a href="https://agentmods.dev/skills/secondlifes/code-intel/rad-code-fix"><img src="https://agentmods.dev/badge/skills/secondlifes/code-intel/rad-code-fix.svg" alt="Measured on agentmods" 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 | $0.00175 | $0.03657 |
| Opus 5 | $0.00088 | $0.01828 |
| Sonnet 5 | $0.00035 | $0.00731 |
| Haiku 4.5 | $0.00017 | $0.00366 |
Grade A, and why
rad-code-fix 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 4d 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.
This is a copy
100% identical to rad-code-fix — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Fix — whole-file, dependency-aware, measured
Provide the process; let the host project provide language, architecture, toolchain, style and test standards. Never invent a project rule from memory.
Modes and boundaries
Infer the narrowest mode that satisfies the request:
| Mode | Outcome |
|---|---|
| Audit-only | Find and prove defects; report them without writing code. |
| Audit + Fix | Audit first, obtain approval, then repair approved findings. |
| Enhancement | Turn a requested feature into acceptance criteria, implement it, and prove it without regressing existing behavior. |
| Apply a report | Take findings someone else already wrote down, re-verify each one against the code as it is now, then repair the approved survivors. |
Discovery is the expensive part, so the mode boundary is really about whether the findings already exist. When the user hands over a report, do not audit from scratch — the report is the scope, and Phase 3b explains why it still has to be checked rather than trusted.
- A diff/PR-only review belongs to the host's diff-review workflow.
- Visual direction and UI aesthetics belong to
frontend-design; UI guideline compliance belongs toweb-design-guidelines. This skill may still audit or implement UI behavior, accessibility and integration correctness. - Load stack-specific skills when present. They supply domain rules; this skill owns orchestration, evidence, scope and verification.
Usage
| The user says | Mode | What happens |
|---|---|---|
"audit parser.py and everything it depends on" |
Audit-only | Baseline, whole-file read, findings with evidence. No file is written. |
"find and fix everything in OrderService.cs" |
Audit + Fix | Findings first, then the mechanical/design split for approval, then one atomic item at a time |
"apply share/analysis/.../codex_v1.md to the skill it reviews" |
Apply a report | Report intake, per-finding re-verification, then the same approval and execution path |
"add a --dry-run flag to the importer" |
Enhancement | Acceptance criteria and non-goals first, then red-first tests, then implementation |
| "review this PR" | none | Belongs to the host's diff-review workflow; say so rather than auditing whole files |
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.
- 4d ago First seen · 347 lines · 175 tokens per session scan A ddc93042af97
rad-code-fix is a skill published in the GitHub repository SecondLifes/code-intel (2 stars, last pushed 7d ago), licensed Apache-2.0. It adds 175 tokens to every session and 3,657 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to rad-code-fix, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
gsd-ns-review
Route to the appropriate quality / review skill based on the user's intent. gsd-code-review-fix was absorbed by gsd-code-review --fix in #2790.
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…
gitnexus
A code-graph analysis add-on for examining an existing codebase, including symbols, call paths, execution flows, and effects across repositories. It can query GitNexus through its command-line or MCP interfaces.
cleanup-code-inspections
Reduce technical debt and improve code quality by systematically resolving static analysis warnings.
superlint
This skill describes the mandatory standard operating procedure for using our internal SuperLint tool. Use this when tasks require fixing code quality issues according to corporate standards.