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 SteveGJones/ai-first-sdlc-practices --skill validategit clone --depth 1 https://github.com/SteveGJones/ai-first-sdlc-practicesWrote 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/stevegjones/ai-first-sdlc-practices/validate)<a href="https://agentmods.dev/skills/stevegjones/ai-first-sdlc-practices/validate"><img src="https://agentmods.dev/badge/skills/stevegjones/ai-first-sdlc-practices/validate.svg" alt="Measured on agentmods" 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 | $0.00030 | $0.01525 |
| Opus 5 | $0.00015 | $0.00763 |
| Sonnet 5 | $0.00006 | $0.00305 |
| Haiku 4.5 | $0.00003 | $0.00153 |
Grade A, and why
validate scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
HTTP_CODE=$(curl -s -o /dev/null -w "%{http_code}" http://127.0.0.1:18080/ 2>/dev/null || echo "000") How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SDLC Validation
Run the validation pipeline at the specified level. Each check calls standard tools directly — no wrapper scripts needed.
Arguments
--syntax— Syntax only (fast, after every edit)--quick— Syntax + lint + tests (before commits)--pre-push— Full pipeline (before PRs). This is the default.
Preflight
Before running any check, verify the tool is available. Report missing tools clearly:
[SKIP] <tool> — not installed (run: <install command>)
Missing tools at --syntax level: warn but continue.
Missing tools at --quick or --pre-push level: report all missing tools, then stop.
Preflight checks
| Tool | Check command | Install command |
|---|---|---|
| ruff | which ruff |
pip install ruff |
| pytest | which pytest |
pip install pytest |
| mypy | which mypy |
pip install mypy |
| bandit | which bandit |
pip install bandit |
Also check:
- Virtual environment active:
which pythonshould contain.venv. If not, warn: "No virtual environment active. Run: source .venv/bin/activate" - Test directory exists:
ls tests/should find test files. Iftests/missing or empty, report: "No tests found. Tests are mandatory (Constitution Article 10.2)."
--syntax (after every edit)
Run these checks:
- Python AST check — verify all .py files parse:
python -c "
import ast, sys, pathlib
errors = []
for f in pathlib.Path('.').rglob('*.py'):
if '.venv' in str(f):
continue
try:
ast.parse(f.read_text())
except SyntaxError as e:
errors.append(f'{f}:{e.lineno}: {e.msg}')
if errors:
print('Syntax errors found:')
for e in errors:
print(f' {e}')
sys.exit(1)
print(f'Syntax OK — {len(list(pathlib.Path(\".\").rglob(\"*.py\")))} files checked')
"
- Ruff syntax errors only (if ruff installed):
ruff check . --select E9,F63,F7,F82
Report results:
[PASS] Syntax check — N files checked, 0 errors
[PASS] Ruff (syntax) — 0 issues
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.
- 8d ago First seen · 199 lines · 30 tokens per session scan A 8376dc4e1a2c
validate is a skill published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 29d ago), licensed MIT. It adds 30 tokens to every session and 1,525 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.