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/helderberto/agent-skills/testnpx skills add helderberto/agent-skills --skill testgit clone --depth 1 https://github.com/helderberto/agent-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 | $0.00086 | $0.00935 |
| Opus 5 | $0.00043 | $0.00467 |
| Sonnet 5 | $0.00017 | $0.00187 |
| Haiku 4.5 | $0.00009 | $0.00093 |
Grade A, and why
test 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 3d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test — Verify
Tests are proof. Confirm the code actually works, then — if a plan exists — verify its claims against the codebase. Works for frontend and backend alike; validation and coverage run against whatever test runner the project uses.
Interactive prompts: present options as a numbered list and wait for the user's choice.
Input
The argument (if provided) is: $ARGUMENTS
Accepts a plan <slug> or @file reference. If omitted, glob .specs/plans/*.md:
- one plan → use it
- several → list as numbered options and wait for the user's choice
- none → run validation only (skip plan verification)
Workflow
1. Validate (always)
Run and collect all results — don't stop at the first failure:
/validate-code— auto-fix formatting/lint, verify types, run the full test suite- Changed-line coverage — if the project emits coverage, confirm the lines you changed (
git diff -U0) are exercised, not just the global %. Skip when the project has no coverage tooling.
Capture pass/fail and any uncovered changed lines.
2. Load the plan (if any)
Read .specs/plans/<slug>.md. If there is no plan, skip to Report with just the validation results.
Fast-path: if the primary module file(s) from Phase 1 don't exist, report 0/N — not yet started, list Phase 1 done-when items, skip the subagent.
3. Verify plan claims (read-only subagent)
Launch a general-purpose subagent (not code-review). It must be read-only — no writes, no edits. It should:
- Read every section of the plan — architectural decisions, each phase, done-when checkboxes
- Check every
- [ ]/- [x]item against the codebase - Fold in the Step 1 test results
- Decide, per checkbox, whether it holds (
[x]) or not ([ ])
Collect findings into two categories:
- BLOCKERS — checked items that don't hold up, failing tests, broken contracts
- SUGGESTIONS — improvements, minor gaps, style issues
4. Update checkboxes
In .specs/plans/<slug>.md: items that pass → [x], items that fail → [ ] (unmark). This is the only file write this skill makes.
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.
- 3d ago First seen · 100 lines · 86 tokens per session scan A 2cd604bf62bf
test is a skill published in the GitHub repository helderberto/agent-skills (13 stars, last pushed 12d ago), licensed MIT. It adds 86 tokens to every session and 935 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 2026-08-30.
Other skills, from other repositories
code-review-and-quality
Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.
constraint-driven-development
Establishes a project's quality bar as a written contract and stops agents quietly lowering it. Interviews the user on which dimensions matter, supplies sane default thresholds when they have no number in mind, records everything in CONSTRAINTS.md, and watches the diff for a weakened bar — new @ts-ignore or…
performance-optimization
Optimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks.
api-and-interface-design
Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.
code-simplification
Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity.
doubt-driven-development
Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production, security-sensitive logic, irreversible operations), or any time a confident output would be cheaper to verify now…