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 agentmods add skills/destynova2/cli-code-skills/cli-audit-datanpx skills add Destynova2/cli-code-skills --skill cli-audit-datagit clone --depth 1 https://github.com/Destynova2/cli-code-skillsWhat 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 | $0.00085 | $0.04117 |
| Opus 5 | $0.00043 | $0.02058 |
| Sonnet 5 | $0.00017 | $0.00823 |
| Haiku 4.5 | $0.00009 | $0.00412 |
Grade A, and why
cli-audit-data 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 2d 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 — 500 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Optimization: Read detailed references only when the audited scope needs them.
Language rule: Write user-facing reports in the project's dominant language. Keep SQL, identifiers, paths, SQLSTATE values, and the mandatory uncertainty marker unchanged.
Audit Data — PostgreSQL and SQLx Safety
Purpose
Detect database code that compiles and passes nominal CRUD tests but violates business logic under concurrency, retries, failures, migration, mixed application versions, or data drift.
Treat the database as a dynamic system that must preserve explicit laws across every transition. Physics, biomimicry, cybernetics and safety engineering are lenses for discovering risks; only constraints, atomic operations, demonstrated transaction protocols and reproducible PostgreSQL tests count as technical proof.
Read ../shared/data-invariants.md before auditing; it owns the cross-skill criticality, invariant,
conservation, interleaving, proof-ladder, and uncertainty contracts. Read ../gotchas.md last.
Non-negotiable rules
- Do not implement before identifying sources of truth and invariants.
- Give every business fact one explicit owner and authoritative source.
- Protect persistent invariants in PostgreSQL; Rust validation alone is not an integrity guarantee.
- Analyze every
read -> decide -> writesequence with at least two concurrent actors. - Give every retryable operation an explicit idempotency protocol.
- Bound, observe and repair every eventually consistent fact.
- Analyze every migration with old code, new code and mixed-version deployment.
- Put all writes of one atomic business decision inside one explicit transaction boundary.
- Never make external network calls while a PostgreSQL transaction is open.
- Never ignore
rows_affected() == 0when zero rows has business meaning. - Never silently edit an already-applied migration.
- Never claim cross-system
exactly oncewithout a demonstrated protocol; use durable identity, idempotence and outbox/inbox patterns. - Never use SQLite or mocks as proof of PostgreSQL concurrency behavior.
- Decide deletion, cascade, retention, anonymization and restoration explicitly.
- Make every derived fact reconstructible or give it an auditable repair protocol.
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.
- 2d ago First seen · 500 lines · 85 tokens per session scan A 62b8f0f65962
cli-audit-data is a skill published in the GitHub repository Destynova2/cli-code-skills (5 stars, last pushed 10d ago), licensed MIT. It adds 85 tokens to every session and 4,117 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
clean-architecture
Apply Robert C. Martin's Clean Architecture, SOLID, and component-decoupling principles when designing, reviewing, or refactoring code — scaled correctly to the size of the task so trivial changes don't get over-engineered. Use this whenever the user asks to design a new feature/service, review code for architectural…
sdlc
Full SDLC workflow for implementing features, fixing bugs, refactoring code, testing, releasing, publishing, and deploying. Use this skill when implementing, fixing, refactoring, testing, adding features, building new code, or releasing/publishing/deploying.
feedback
Submit feedback, bug reports, feature requests, or share SDLC patterns you've discovered. Privacy-first — always asks before scanning.
deploy
Deploy the application to production.
claude-setup-wizard
Setup wizard — scans codebase, builds confidence per data point, only asks what it can't figure out, generates SDLC files. Use for first-time setup or re-running setup.
claude-update-wizard
Smart update for SDLC wizard — shows changelog, compares files, lets you selectively adopt changes while preserving customizations.