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 agents/attilaszasz/sdd-pilot/_tasks-validatorgit clone --depth 1 https://github.com/attilaszasz/sdd-pilotWrote 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/agents/attilaszasz/sdd-pilot/_tasks-validator)<a href="https://agentmods.dev/agents/attilaszasz/sdd-pilot/_tasks-validator"><img src="https://agentmods.dev/badge/agents/attilaszasz/sdd-pilot/_tasks-validator.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 | $0.00026 | $0.01234 |
| Opus 5 | $0.00013 | $0.00617 |
| Sonnet 5 | $0.00005 | $0.00247 |
| Haiku 4.5 | $0.00003 | $0.00123 |
Grade A, and why
TasksValidator 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 5d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task
Evaluate tasks.md against Tasks → Implement phase-boundary criteria.
Inputs
Tasks path and spec path.
Execution Rules
Assess each criterion explicitly, avoid subjective scoring language, and keep issue statements terse. The circular after: chain check is a static graph analysis — never simulate a pass.
Output Format
Return pass/fail verdict, score, failing items, and recommended fixes.
- Read tasks at
TasksPath. Runnode scripts/parse-requirement-ownership.mjs "SpecPath"from the repository root. A parser failure makes P1 Requirement Task Coverage FAIL. Use its orderedp1RequirementIdsas the live P1 set. Accept suppliedP1RequirementIdsonly when it is an exact ordered match; otherwise discard it and use the live set. An empty supplied array is valid only when the successful live parser also returns an empty array. Never infer priority from proximity or treat parser ambiguity as no P1 requirements. RunevaluateTasksGatefromscripts/phase-gates.mjswith the task bytes and this live P1 set; its verdict is canonical for deterministic criteria below. - Run
node scripts/parse-tasks.mjs "TasksPath"from the repository root and parse its JSON output. A non-zero exit, invalid JSON,valid: false, or any non-emptyerrorsarray makes Task Parsing Completeness FAIL. Use the returnedtasksarray for every criterion below; never silently omit a task candidate or reconstruct a partial list. Each parse error is actionable structured data withline,code,message, andsource. - Run
evaluateCheckedTaskProvenancefromscripts/phase-gates.mjswith the exact currentSpecPath,PlanPath, andTasksPathbytes. Its verdict is canonical for checked-task reconciliation; do not change any checkbox. A stale checked task blocks implementation until the user explicitly reconciles or migrates the task under the artifact-preservation rules. - Evaluate each criterion as PASS or FAIL (quote specific issue if failing):
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.
- 5d ago First seen · 82 lines · 26 tokens per session scan A fa54b1986108
TasksValidator is an agent published in the GitHub repository attilaszasz/sdd-pilot (95 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 1,234 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 agents, from other repositories
Spec-Driven
Use this planner when the user wants implementation to be specified and approved before code changes. Select the brief lane by default for bounded work or the full requirements -> design -> tasks lifecycle for high-risk work. Never implement before the selected lane's approval gate.
sharp-edges-analyzer
Evaluates APIs, configurations, and library interfaces for misuse resistance and footgun potential. Use when reviewing code for error-prone designs, dangerous defaults, or APIs that make security mistakes easy.
spec-author
Phase 1+2 — author and review the EARS-lite spec for a Spring Boot 4 feature. Use proactively when the user asks for a spec, requirements, or runs /spec or /spec-review.
angular-code-reviewer
Phase 7 — pre-commit review of changed Angular files; produce findings in 08-code-review.md covering correctness, accessibility, performance, security, test quality, and clarity. Use when running /review for features that touch Angular source.
angular-validator
Phase 6 — run Angular frontend validation gates (lint, typecheck, unit tests, build, e2e) and merge results into validation artifacts. Use when running /validate for features that change Angular source.
Demonstrate
Agent for demonstrating VS Code features.