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-for-suregit 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-for-sure)<a href="https://agentmods.dev/skills/ai-driven-dev/framework/09-for-sure"><img src="https://agentmods.dev/badge/skills/ai-driven-dev/framework/09-for-sure/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-for-sure"><img src="https://agentmods.dev/badge/skills/ai-driven-dev/framework/09-for-sure.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 | $0.00053 | $0.00491 |
| Opus 5.5 | $0.00021 | $0.00196 |
| Sonnet 5.5 | $0.00011 | $0.00098 |
| Haiku 4.5 | $0.00005 | $0.00049 |
Grade A, and why
09-for-sure 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.
How it starts
The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: for-sure
Run an autonomous loop until a success condition is verified. An interactive pre-flight (human present) sets it up, then autonomous execution (human gone) retries until success, acting as the user and never stopping early.
Actions
| # | Action | Phase | Role |
|---|---|---|---|
| 01 | init-tracking |
interactive pre-flight | validate the goal, build the journey map, create the tracking file, spawn the loop |
| 02 | auto-accept |
autonomous | decide and act as the user, stopping only on money or destructive actions |
| 03 | autonomous-loop |
autonomous | spawn one worker per step, verify, retry, evaluate the success condition |
Run 01 interactively; it spawns 03, which runs unattended under the 02 auto-accept rules until the success condition passes.
Before running an action, read its file in actions/, not only the table or assets.
Transversal rules
- Single source of truth: all task state lives in
aidd_docs/tasks/<task-name>.mdand nowhere else. - No repeated failures: never retry a failed approach without a meaningful change.
- Honesty over escape: never set
status: implementeduntil the success condition genuinely passes. - Auto-accept: when a decision or approval is needed, act as the user (create accounts, generate keys, approve prompts, install tools), never asking. Stop only on a payment or a destructive action.
- The loop spawns one worker agent per step and never does the work itself.
Assets
assets/plan-template.md: the tracking file format (frontmatter, phases, acceptance criteria, Log).assets/autonomous-loop-worker-prompt.md: the prompt the loop spawns each per-step worker with.
References
references/autonomous-loop-log-format.md: the Log entry format the loop appends per attempt.
What ships with it
6 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.
- 1mo ago First seen · 38 lines · 53 tokens per session scan A 878a0987258a
09-for-sure is a skill published in the GitHub repository ai-driven-dev/framework (537 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 491 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
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.
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.
bad-case-to-dpo
A guide to turning failed production agent runs into training and evaluation data. It explains how to find the first mistake, create preference examples for DPO (Direct Preference Optimization), and check that a fix does not damage other tasks.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
self-improve-with-tinyfish
Enables Hermes to create new reusable skills for itself by researching live web sources with TinyFish Search and Fetch, analyzing source coverage, writing SKILL.md files, and installing them into Hermes memory. Use when the user asks Hermes to learn, teach itself, upgrade itself, or save a reusable capability.
tech-stack-detective
Reverse-engineer a company's tech stack from public signals — job listings, StackShare, GitHub, engineering blog, and their live website. Use this skill when a user asks "what tech does Stripe use", "what's Linear's stack", "what does Notion run on", "reverse engineer [company]'s tech stack", "what framework does…