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 qte77/claude-code-plugins --skill hardening-codebasegit clone --depth 1 https://github.com/qte77/claude-code-pluginsWrote 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/qte77/claude-code-plugins/hardening-codebase)<a href="https://agentmods.dev/skills/qte77/claude-code-plugins/hardening-codebase"><img src="https://agentmods.dev/badge/skills/qte77/claude-code-plugins/hardening-codebase/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/qte77/claude-code-plugins/hardening-codebase"><img src="https://agentmods.dev/badge/skills/qte77/claude-code-plugins/hardening-codebase.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 | $0.00044 | $0.01094 |
| Opus 5.5 | $0.00018 | $0.00438 |
| Sonnet 5.5 | $0.00009 | $0.00219 |
| Haiku 4.5 | $0.00004 | $0.00109 |
Grade A, and why
hardening-codebase 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harden Codebase
Scope: $ARGUMENTS (default: full)
Systematic quality tightening. Nine phases, each with a clear gate. KISS: tighten one level at a time — never jump to max strictness.
Phase 1: ARCHITECTURE (read-only)
- Identify entry points, module boundaries, and dependency flow
- Map layering: which modules depend on which?
- Flag circular dependencies and boundary violations
- Output module map as indented text tree (plain markdown, no diagrams)
- Note undocumented coupling, god modules, misplaced responsibilities
Gate: Module map + issue list. Present to user before proceeding.
Phase 2: AUDIT (read-only)
- Does
make setup_all(or equivalent) work from scratch? - What lint rules are enabled? Gap vs recommended?
See
references/lint-tightening-checklist.md - Type checker strictness level?
- Do tests pass? Are slow/hardware tests filtered?
- Is check-only gate separate from auto-fix?
Gate: Issue list ranked HIGH/MEDIUM/LOW. Present to user before proceeding.
Phase 3: TIGHTEN (config only — no code changes)
- Enable next-level lint rules (baseline → recommended, not strict)
- Bump type checker one level
- Split auto-fix from check-only gate if missing
- Add test marker filters for slow/hardware/network
- Count new violations — report before fixing
Gate: Config committed. Violation count known.
Phase 4: FIX (mechanical)
- Run auto-fix
- Fix remaining violations manually
- Update tests broken by signature changes
make validatemust pass
Gate: All checks green. Commit fixes.
Phase 5: DOCS QUALITY
- Does README exist and reflect current state?
- Are public APIs documented (docstrings, JSDoc, rustdoc)?
- Are architecture decisions recorded (ADRs or equivalent)?
- Do inline comments explain why, not what?
- Are there stale/misleading docs that contradict the code?
- Enforce KISS in docs — no walls of text, no redundant sections
- Enforce DRY — single source of truth, no copy-pasted explanations
- Enforce YAGNI — remove docs for features that don't exist
What ships with it
2 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 · 127 lines · 44 tokens per session scan A 24cc41579608
hardening-codebase is a skill published in the GitHub repository qte77/claude-code-plugins (3 stars, last pushed 4d ago), licensed Apache-2.0. It adds 44 tokens to every session and 1,094 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
codex-advisor
Advisory consultation skill for architectural reviews, design decisions, code analysis, and technology evaluation. Codex provides recommendations without making code changes. Invoked by phrases like "consult Codex", "get Codex's opinion", "ask Codex about", "have Codex review", "Codex analysis", "validate this…
code-review
Review code for actionable defects. Correctness is the core; performance and security are optional sub-cases of the same engine. Anchors on agreements between participants across a boundary, forces a violating execution, and refutes every candidate before reporting. Use when asked to review changes, find bugs, audit a…
intended-vs-implemented
The method for finding the gap between what a system is supposed to do and what the code actually does — the class of bug generic scanners miss because they have no model of intent. Defines what counts as documented intent, what counts as implementation evidence, which mismatches matter, and how to avoid hand-wavy…
improve-code-quality
Guided journey from a working-but-untested vibe-coded prototype to a production-ready product with tests, clean structure, a business-rules boundary, and resilience at scale. Orchestrates nine skills phase by phase - working-with-legacy-code, clean-code, refactoring-patterns, software-design-philosophy…
refactoring-patterns
Apply named refactoring transformations to improve code structure without changing behavior. Use when the user mentions "refactor this", "code smells", "extract method", "replace conditional", "technical debt", "move method", "inline variable", "decompose conditional", or "clean up this messy code". Also trigger when…
team-review
Review changed code for reuse, quality, and efficiency using a team of persistent named reviewers. This skill should be used when the user says "team review", "review with team", or wants parallel code review with persistent team members for follow-up questions. Similar to /subagent-review but reviewers persist after…