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 AgentureHQ/agenture-loop --skill validategit clone --depth 1 https://github.com/AgentureHQ/agenture-loopWrote 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/agenturehq/agenture-loop/validate)<a href="https://agentmods.dev/skills/agenturehq/agenture-loop/validate"><img src="https://agentmods.dev/badge/skills/agenturehq/agenture-loop/validate/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/agenturehq/agenture-loop/validate"><img src="https://agentmods.dev/badge/skills/agenturehq/agenture-loop/validate.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00032 | $0.02379 |
| Opus 5.5 | $0.00013 | $0.00952 |
| Sonnet 5.5 | $0.00006 | $0.00476 |
| Haiku 4.5 | $0.00003 | $0.00238 |
Grade A, and why
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 2mo 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validate (/agn:validate <level>)
Arguments
| Position | Variable | Value |
|---|---|---|
$0 |
level | task, feature, epic, or product |
$1 |
id | Optional task path (for task) or scope hint (for feature / epic) |
Argument validation
If $0 is missing, stop and ask:
"What level — task, feature, epic, or product?"
If $0 is not one of task, feature, epic, product, stop and list the valid set.
Dispatch
Read $0. Run exactly one of the branches below.
Validation via the QA sub-agent
For feature, epic, and product levels, validation runs in the QA sub-agent (plugins/agn/agents/qa.md). The sub-agent loads rules/qa.md, reads the spec and the implementation, runs tests, and returns a verdict. Fresh context is the point — the agent that wrote the code has already collapsed the design space in their head; a fresh reader sees gaps that closed space hid.
The task branch does not invoke the QA sub-agent — the task's own ## Quality gates are narrow and the parent session has the right context to run them.
When a workflow below says "delegate to QA", invoke it via the Agent tool with subagent_type: qa and a brief containing:
level—feature|epic|productscope— slug (feature/epic) or "whole product"spec_paths— paths to relevant documents (docs/vision.md,docs/spec.md,docs/requirements.md,docs/architecture.md, parent epic/feature file, linked spec)implementation_paths— files, test commands, dev-server URLs, sample data locationsregression_scope(optional) — adjacent features/areas to re-check
QA returns a structured response (## Verdict, ## Per-requirement results, ## Issues by severity, ## What I fixed, ## What I escalated, ## Report path, ## Next steps). Surface the verdict to the user. On not ready, present the issues and stop — do not silently advance the lifecycle (e.g., do not auto-close a feature whose QA verdict was not ready).
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.
- 2mo ago First seen · 168 lines · 32 tokens per session scan A 9b704cd8d443
validate is a skill published in the GitHub repository AgentureHQ/agenture-loop (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 2,379 once invoked, about $0.0001 per session on Opus 5.5. 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
linked-intent-dev
Guide for linked-intent development (LID). Consult for ALL code changes. Walks changes through a mode-aware six-phase workflow (HLD → LLD → EARS → intent-narrowing edge audit → tests-first → code) with mandatory stops between each phase. Bugs walk the arrow like any other change — no short-circuit. Enforces cascade…
auto-loop
TDD-based autonomous development loop with checkpoint recovery and observability changelog.
workflow
Run the complete 5-step development workflow: focus problem → prevent over-development → test-first (TDD) → document → smart commit. Use when starting a new feature, or when the user runs /workflow or asks for the full development flow.
test-runner
Test execution reference: framework detection (pytest/jest/vitest/go/cargo/junit) and correct run/coverage commands, plus failure-analysis steps. Use when running tests, analyzing test failures, or verifying coverage after code changes.
test-first
Drive one feature through a strict TDD Red-Green-Refactor cycle with checklists for each phase. Use when implementing new functionality test-first, or when the user runs /test-first.
bidirectional-differential
Audit coherence across an arrow of intent by running two parallel fresh Claude sessions — one reconstructs code from a single EARS, the other reconstructs the EARS from stripped code — then classifies the drift between them. Use when the user invokes /differential-audit, asks to audit EARS-to-code drift for a feature…