Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/aget-framework/template-advisor-agetnpx agentmods add skills/aget-framework/template-advisor-aget/aget-release-critiqueWrote 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/aget-framework/template-advisor-aget/aget-release-critique)<a href="https://agentmods.dev/skills/aget-framework/template-advisor-aget/aget-release-critique"><img src="https://agentmods.dev/badge/skills/aget-framework/template-advisor-aget/aget-release-critique/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/aget-framework/template-advisor-aget/aget-release-critique"><img src="https://agentmods.dev/badge/skills/aget-framework/template-advisor-aget/aget-release-critique.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 | $0.00000 | $0.01880 |
| Opus 5 | $0.00000 | $0.00940 |
| Sonnet 5 | $0.00000 | $0.00376 |
| Haiku 4.5 | $0.00000 | $0.00188 |
Grade A, and why
aget-release-critique 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 10d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/aget-release-critique
Adversarial review with the Critic perspective of the Release Delivery Triad (L818). Dual-mandate: spec coverage audit + deep bug finding.
Purpose
The Critic asks: "What will break in the field? What assumptions are wrong? Does the spec match reality?"
This skill shifts your cognitive posture to adversarial skepticism. You believe nothing until proven. Every claim is a hypothesis. Every assumption is a potential failure. You are the Critic — find what the Builder missed and what the Spec Auditor couldn't see.
You do NOT execute deliverables (that is /aget-release-build). You do NOT write or fix specs (that is /aget-release-audit-specs + principal). You critique.
Triggers
- "critique gate", "critique release"
- "adversarial review"
/aget-release-critique
Input
Optional: gate number, Builder report, Spec Auditor report. If available, use sibling reports to focus critique. If not, perform independent adversarial review.
Execution
Step 1: Establish Critique Scope
Identify what was produced in this gate:
- Deliverables from Builder report (or PROJECT_PLAN)
- Spec findings from Auditor report (if available)
- Any artifacts created or modified
Step 2: Mandate 1 — Spec-to-Reality Coverage Audit
For each deliverable and spec in scope:
Ask these questions:
- Does the implementation actually do what the spec says it does?
- Are there behaviors in the implementation that have no spec coverage?
- Are there spec requirements that the implementation doesn't enforce?
- Are there sleeping requirements — spec text with no downstream consequence (L671)?
Method: Read the spec. Read the implementation. Compare. Every gap is a finding.
Step 3: Mandate 2 — Adversarial Deep-Bug Finding
For each deliverable in scope:
Assumption surfacing:
- What are we assuming about the input? What if it's different?
- What are we assuming about the environment? What if it changes?
- What are we assuming about downstream consumers? What if they use this differently?
- What would a hostile or confused user do with this?
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.
- 10d ago First seen · 182 lines · 0 tokens per session scan A 09a388e80653
aget-release-critique is a skill published in the GitHub repository aget-framework/template-advisor-aget (2 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,880 tokens. 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
pir-action-tracker
Parses Post-Incident Review (PIR) pages in a Confluence space, fetches live status from referenced Jira tickets, updates action item tables with current status and due dates, marks completed PIRs with a visual closure panel, and surfaces any overdue actions for follow-up. Designed for Customer Success, Support, and…
check
Run the full local quality gate (prek hooks + tox test matrix) before committing or opening a pull request. Use when asked to "check", "lint", "run CI locally", or verify a change is ready.
code-review-python
Deep Python-specific code review covering type annotations, async pitfalls, mutable defaults, threading safety, and domain modeling. Applied in addition to the generic code-review skill when Python code is detected. Invoked when reviewing Python PRs, Py changes, or performing Python-specific quality checks.
agentic-preflight
Use when shipping a branch — reviewing, documenting, linting, testing, and pushing work behind a quality gate. Also use when a push is blocked by the agentic-preflight pre-push hook or when the user says agentic-preflight:uninstall to remove this tool from the current project.
heaven-style
Use when coding, designing, reviewing, or writing documentation in TypeScript or Python projects.
karpathy-guidelines
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.