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 09-defectgit 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/09-defect)<a href="https://agentmods.dev/skills/ai-driven-dev/framework/09-defect"><img src="https://agentmods.dev/badge/skills/ai-driven-dev/framework/09-defect/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/09-defect"><img src="https://agentmods.dev/badge/skills/ai-driven-dev/framework/09-defect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00049 | $0.00267 |
| Opus 5.5 | $0.00020 | $0.00107 |
| Sonnet 5.5 | $0.00010 | $0.00053 |
| Haiku 4.5 | $0.00005 | $0.00027 |
Grade A, and why
09-defect 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 1mo 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
Defect
flowchart LR
source([report or Defect]) --> capture --> assess --> finalize
source -->|"already persisted"| finalize
assess -->|"revise"| capture
finalize -->|"revise"| capture
finalize -->|"authorized"| done([Defect])
Actions
Run the flow above. Read only the next action file.
| Action | Does |
|---|---|
| capture | frame one observed product mismatch |
| assess | establish evidence, impact, and readiness |
| finalize | persist or transition the Defect |
Transversal rules
- Keep product and lifecycle decisions with the user.
- Separate evidence, decisions, and assumptions.
- Preserve source links and existing edits.
- Ask natural questions; never expose actions, references, or unchanged state.
- Require explicit approval or caller-provided bounded authority before any write.
- Record the mismatch; never diagnose or implement its fix.
What ships with it
10 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.
- actions/01-capture.md 1.1 KB
- actions/02-assess.md 897 B
- actions/03-finalize.md 1.6 KB
- assets/defect-template.md 471 B
- references/handoffs.md 521 B
- references/lifecycle.md 783 B
- references/persistence.md 769 B
- references/qualification.md 193 B
- references/readiness.md 543 B
- references/relations.md 790 B
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.
- 1mo ago First seen · 36 lines · 49 tokens per session scan A 2c91a61f33fd
09-defect is a skill published in the GitHub repository ai-driven-dev/framework (522 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 267 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
awesome-ai-agents-curation
Help founders prepare evidence-backed AI agent project submissions and help maintainers triage project issues and pull requests for the Awesome AI Agents list.
ship-it
Worktree-side implementation orchestrator for an OpenSpec change. Idempotent: gates automated scenarios on filesystem reality, owns the red-test fix loop, runs the docker harness with always-teardown, then drives ship-change inline. Escape hatch writes SHIPITBLOCKED.md. Runnable headless. Triggers: "ship it", "build…
task-graph
Execute an approved multi-task plan as a verified DAG with @taskgraph — parallel squad workers per task, validation gates the engine runs itself, and an independent reviewer verdict before any task counts as done. Use for deliveries of 5+ tasks with real independence between them; for smaller work dispatch workers…
linear
Manage Linear issues from the terminal via the official GraphQL API and the user's API key — list/search issues, create issues, update status/assignee, add comments. Use when asked to "create a Linear issue", "what's assigned to me in Linear", "move this issue to done", "comment on LIN-123".
notion
Read and write Notion — search pages/databases, query a database, create pages, append blocks — via the official Notion REST API and the user's own integration token. Use when asked to "add to Notion", "find in my Notion", "create a Notion page", "update my Notion database".
caixun-work-hours
A work-hours reporting assistant for RichPMS, a project time-tracking system. It turns conversation details, code records, or your description into a daily report, lets you confirm it, and then saves or submits it.