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 commands/zekiriabd/sdd-pro/feat-validategit clone --depth 1 https://github.com/zekiriabd/SDD-ProWrote 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/commands/zekiriabd/sdd-pro/feat-validate)<a href="https://agentmods.dev/commands/zekiriabd/sdd-pro/feat-validate"><img src="https://agentmods.dev/badge/commands/zekiriabd/sdd-pro/feat-validate.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 | $0.00023 | $0.05297 |
| Opus 5 | $0.00012 | $0.02648 |
| Sonnet 5 | $0.00005 | $0.01059 |
| Haiku 4.5 | $0.00002 | $0.00530 |
Grade A, and why
feat-validate 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 4d 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 — 415 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/feat-validate — Implementation Readiness Gate (déterministe, v6.1)
Vérifie qu'une FEAT + ses US + mockups HTML sont prêts pour /dev-run.
Validation 100% déterministe via Python (validate_readiness.py
validate_semantic.py, 0 token LLM, 0 agent invoqué).
v6.1 (réintroduction validation sémantique low-cost) : à la couche
structurelle (readiness) s'ajoute une couche sémantique déterministe
(vocabulaire + regex) qui détecte ambiguïtés, AC non mesurables,
keywords sécurité sans mécanisme de protection, PII sans mention de
privacy, et routes /api/* mentionnées sans endpoint backend déclaré.
Toujours 0 token LLM ; WARN non bloquant par défaut.
Usage :
/feat-validate {n}— valide la FEAT{n}et produit le rapport/feat-validate {n} --json— sortie JSON pour CI/CD (n'affecte QUE le format de sortie — ne bypasse JAMAIS la spec-compliance gate STEP 4.5, cf. FWD-C3 fix 2026-06-12)/feat-validate {n} --post-dev— forceMODE=post-dev(active la spec-compliance gate STEP 4.5 sans dépendre de l'heuristiqueHAS_CODE). Utilisé par/sdd-fullSTEP 4.7. Combinable avec--json.
Décisions possibles :
- 🟢 GO : prêt pour
/dev-run - 🟡 WARN : passable mais review humaine recommandée
- 🔴 NO-GO : bloque
/dev-run(sauf/dev-run {n} --force)
STEP 1 — Valider l'argument
Argument obligatoire : {n} (entier ≥ 1).
Flags optionnels (parsés ici, ordre libre) :
--json→JSON_FLAG=1(format de sortie JSON, cf. Mode JSON)--post-dev→POST_DEV_FLAG=1(forceMODE=post-devau STEP 4.5.1)
Tout autre flag inconnu → ignoré silencieusement (forward-compat).
Si absent →
ERROR: /feat-validate — argument manquant
CAUSE: [INVALID_ARG] aucun numéro de FEAT fourni
FIX: relancer /feat-validate {n} (ex. /feat-validate 1)
Si non numérique →
ERROR: /feat-validate — argument invalide
CAUSE: [INVALID_ARG] "{argument}" n'est pas un entier
FIX: relancer /feat-validate {n}
STEP 2 — Localiser la FEAT
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.
- 4d ago First seen · 415 lines · 23 tokens per session scan A 0742929a5383
feat-validate is a command published in the GitHub repository zekiriabd/SDD-Pro (190 stars, last pushed yesterday), licensed Apache-2.0. It adds 23 tokens to every session and 5,297 once invoked, about $0.0001 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.