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 lindoelio/spec-driven-steroids --skill code-review-hardeninggit clone --depth 1 https://github.com/lindoelio/spec-driven-steroidsWrote 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/lindoelio/spec-driven-steroids/code-review-hardening)<a href="https://agentmods.dev/skills/lindoelio/spec-driven-steroids/code-review-hardening"><img src="https://agentmods.dev/badge/skills/lindoelio/spec-driven-steroids/code-review-hardening/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/lindoelio/spec-driven-steroids/code-review-hardening"><img src="https://agentmods.dev/badge/skills/lindoelio/spec-driven-steroids/code-review-hardening.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00070 | $0.02490 |
| Opus 5 | $0.00035 | $0.01245 |
| Sonnet 5 | $0.00014 | $0.00498 |
| Haiku 4.5 | $0.00007 | $0.00249 |
Grade A, and why
code-review-hardening 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 — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review Hardening
Strengthen code against defects through systematic, type-aware review. Every reviewed line is understood or explicitly scoped-out. Findings are classified by severity and fixability. The agent applies direct fixes autonomously and re-reviews before producing a final report.
Gotchas
Passive review is incomplete: A static report is a human review. For an autonomous agent, after classifying findings the skill must enter the self-repair loop — apply fixes, re-review, iterate.
Wrong strategy for the type: A hotfix and a new feature require
opposite postures. Applying a full-scope feat review to a hotfix
causes unnecessary delay. Always determine the change type first.
Blocking on style preference: Only block on style if the project's
style guide explicitly requires it. Personal style preferences are
Nit: — never gates.
Skipping lines: Every human-written line must be understood or explicitly scoped-out with a note.
Mentoring vs. blocking: Label every educational comment
Mentoring: so the author knows it is not a gate.
Over-engineering: Block implementations that solve future problems the author doesn't know they'll face. Solve today's problem well.
Quick Start
Input: Files or directories to review, optional change type tag
(feat | fix | hotfix | refactor | migrate | docs)
Output: Structured markdown review report with fix status
Workflow:
1. Determine change type (auto-detect or explicit)
2. Gather project context (style guide, conventions, docs)
3. Review per type strategy — read every line
4. Classify findings by severity AND fixability
5. Self-repair loop — apply direct fixes, re-review (max 3 passes)
6. Author review — remaining author-required items
7. Final verdict + escalation if needed
Activation
Load this skill when:
- User asks for a code review of any kind
- User mentions PR review, pull request review, code review, change review, or review this
- User asks to review specific files, a branch, or a diff
- User wants feedback on a CL (changelist)
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.
- 9d ago First seen · 296 lines · 70 tokens per session scan A 0f44eb59be8a
code-review-hardening is a skill published in the GitHub repository lindoelio/spec-driven-steroids (54 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 2,490 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 2026-08-30.
Other skills, from other repositories
artifact-conventions
Defines preservation, format, and section rules for SDD specification artifacts (spec.md, plan.md, tasks.md, checklists). Use when editing feature-artifact files under specs/ / to prevent accidental corruption of cross-referenced IDs, priorities, and gating state.
plan-authoring
Reference material for writing implementation plans (technical context, architecture decisions, data models, API contracts, project-instructions alignment). Loaded on demand by plan-feature; not directly invokable.
task-generation
Reference material with the canonical task-format grammar and decomposition rules for plan-to-tasks expansion. Loaded on demand by generate-tasks; not directly invokable.
adr-authoring
Defines the canonical MADR format, lifecycle rules, numbering policy, and SAD catalog contract for standalone ADRs under specs/adrs/.
implementation-standards
Reference material with coding standards (defensive coding, error handling, testing patterns). Loaded on demand by the Developer sub-agent (.github/agents/developer.md); not directly invokable.
spec-authoring
Reference material for writing product, technical, and operational specifications (work-item priorities, requirement families, success criteria). Loaded on demand by specify-feature; not directly invokable.