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 ai-driven-dev/framework --skill 03-assertgit clone --depth 1 https://github.com/ai-driven-dev/frameworkWrote 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/ai-driven-dev/framework/03-assert)<a href="https://agentmods.dev/skills/ai-driven-dev/framework/03-assert"><img src="https://agentmods.dev/badge/skills/ai-driven-dev/framework/03-assert/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/ai-driven-dev/framework/03-assert"><img src="https://agentmods.dev/badge/skills/ai-driven-dev/framework/03-assert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 5 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00039 | $0.00395 |
| Opus 5.5 | $0.00016 | $0.00158 |
| Sonnet 5.5 | $0.00008 | $0.00079 |
| Haiku 4.5 | $0.00004 | $0.00040 |
Grade A, and why
03-assert 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.
What it actually says
Skill: assert
Validate that the work behaves as intended: run the project's assertions, iterating and fixing until they pass.
Actions
| # | Action | Facet |
|---|---|---|
| 01 | assert |
Run the project's coding assertions, fixing until they pass |
| 02 | assert-architecture |
Report where the code breaks the documented architecture |
| 03 | assert-frontend |
Inspect the running UI, fixing until the behavior is right |
Run every applicable facet by default, or one when named. Coding (01) always applies; add 03 when the work has a UI and a frontend is running, the facet resolving the URL itself; run 02 only when architecture conformance is asked for. Skip a facet whose precondition is absent, with a noted reason. Ask only when the intent is genuinely ambiguous.
Before running an action, read its file in actions/, not only the table or assets.
Transversal rules
- Gate: it returns a pass or fail verdict on the work.
- Fix loop: the coding and frontend facets fix and re-run until they pass. The architecture facet only reports, never fixes.
- Stop only when every selected assertion passes a final clean sweep.
- On supplied CI failures, fixing facets collect all failed checks, repair each reproducible failure locally, and rerun every applicable command in the final sweep; the caller pushes once after green if authorized, with CI-only checks unverified.
Assets
assets/task-template.md: the tracking file the frontend facet fills across its fix loop.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed 9c4b198c3636
- 1mo ago First seen · 32 lines · 39 tokens per session scan A ee47757d1f7b
03-assert is a skill published in the GitHub repository ai-driven-dev/framework (523 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 395 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Structured root-cause debugging loop — reproduce, isolate, form a hypothesis, verify the fix. Use whenever a bug, crash, test failure, or unexpected behavior is reported.
reproduce-bug
Reproduce a reported bug in googleapis/mcp-toolbox and decide whether it is real, delivering an evidence-backed verdict: confirmed, already fixed, misconfiguration, client-side, works as intended, not reproducible, or blocked. Use whenever a maintainer asks you to reproduce, verify, confirm, or investigate a bug…
fix-failing-tests
Diagnose a failing test in the googleapis/mcp-toolbox repo and land a fix by reasoning from the actual error: read the failure, reproduce it, shrink it until the cause is forced into the open, then fix the cause. Use this whenever a test or CI job is red, a build breaks after a change, many packages fail at once, or a…
loop-engineering
A guide to building reliable loops for AI agents that plan, act, check their work, and continue until a task is truly complete. It includes independent verification and a proposer-reviewer pattern in which one agent's work is checked using outside evidence.
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
agent-evaluation
A guide to measuring whether an AI agent works reliably on the tasks that matter. It covers repeatable test environments, program checks, human-like scoring rules, failure analysis, and experiments that separate model problems from system problems.