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 dayvisonassis/sdd-skills --skill evaluatorgit clone --depth 1 https://github.com/dayvisonassis/sdd-skillsWrote 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/dayvisonassis/sdd-skills/evaluator)<a href="https://agentmods.dev/skills/dayvisonassis/sdd-skills/evaluator"><img src="https://agentmods.dev/badge/skills/dayvisonassis/sdd-skills/evaluator.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 | $0.00117 | $0.03220 |
| Opus 5 | $0.00059 | $0.01610 |
| Sonnet 5 | $0.00023 | $0.00644 |
| Haiku 4.5 | $0.00012 | $0.00322 |
Grade A, and why
evaluator 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 7d 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evaluator
A second, independent layer of validation. After implement-feature finishes a feature, the evaluator looks at it from the outside and confirms — against contract.md — whether the delivery conforms. It finds deviations the implementer's self-check missed. It does not fix code; it evaluates and orchestrates the correction loop, dispatching fix-runner on failure.
Base docs:
https://github.com/dayvisonassis/sdd-skills/blob/main/docs/Skill_Evaluator.md(full rationale),https://github.com/dayvisonassis/sdd-skills/blob/main/docs/Contrato_de_Feature.md(contract structure),https://github.com/dayvisonassis/sdd-skills/blob/main/docs/Como_criar_gates.md(gates),https://github.com/dayvisonassis/sdd-skills/blob/main/docs/Fluxo_SDD_e_Implementacao_das_Skills.md(flow, states, progress.json schema). Report schema:references/evaluation-report-schema.md.
The evaluator complements automated tests — it does not replace them.
INPUT
Free-form. The skill needs:
- The target feature (ID/name) — explicit and required. Abort if absent or ambiguous (list candidates).
- Auto-discovers:
progress.json(root ofdocs/) and the feature'scontract.md(indocs/<feature-id>-<kebab>/). - Optional free-form overrides at the end — e.g. "no screenshots", "gates only", "max 5 attempts" (overrides
maxFixAttemptsfor this run).
If the feature has no contract.md, abort: "No contract.md for F — generate it with spec-writer first."
OUTPUT
- Screenshots — visual evidence of observable UI criteria (when applicable).
- Report — consolidated ✓ / ✗ / — per contract criterion and gate.
- Findings in chat — textual summary for the user.
- State in
progress.json— CLEAN | FAIL | PENDING | ABORTED for the feature. - On FAIL: a structured
evaluation-report.jsonin the feature folder, with each failure classified bykind(consumed byfix-runnerfor code, or a test-writer for tests). - The evaluator does not edit code or tests itself. Code corrections →
fix-runner; test corrections → the matching test-writer (confirmed by the matching test-validator).
What ships with it
1 file 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.
- 7d ago First seen · 204 lines · 0 tokens per session scan A a739f3d9b5ad
evaluator is a skill published in the GitHub repository dayvisonassis/sdd-skills (1 stars, last pushed 11d ago), licensed MIT. It adds 117 tokens to every session and 3,220 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
test-first-bugs
Enforces a test-driven bug-fixing workflow. Use when a user reports a bug, failing code, an error, or asks to fix something.
coverage-enhancer
Analyze existing test suites and source code to suggest additional unit tests that improve test coverage. Use this skill when working with test files and source code to identify untested code paths, missing edge cases, uncovered branches, untested error conditions, and gaps in test coverage. Supports major testing…
directed-test-input-generator
Generate targeted test inputs to reach specific code paths and hard-to-reach behaviors in Python code. Use when: (1) Targeting uncovered branches or specific execution paths, (2) Need coverage-guided test generation, (3) Want to leverage LLM understanding of code semantics for meaningful test inputs, (4) Testing…
java-code-review
Review Java code for bugs, duplicate code, correctness risks, maintainability improvements, and missing tests. By default review files modified in git; when the user explicitly names files, classes, packages, or a diff, review that scope instead. Generate a detailed review.md report with actionable comments and fixes.
incremental-python-programmer
Takes a Python repository and natural language feature description as input, implements the feature with proper code placement, generates comprehensive tests, and ensures all tests pass. Use when Claude needs to: (1) Add new features to existing Python projects, (2) Implement functions, classes, or modules based on…