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 vignesh2027/AI-AGENT-SKILLS --skill doubt-driven-developmentgit clone --depth 1 https://github.com/vignesh2027/AI-AGENT-SKILLSWrote 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/vignesh2027/ai-agent-skills/doubt-driven-development)<a href="https://agentmods.dev/skills/vignesh2027/ai-agent-skills/doubt-driven-development"><img src="https://agentmods.dev/badge/skills/vignesh2027/ai-agent-skills/doubt-driven-development.svg" alt="Measured on agentmods" 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 | $0.00014 | $0.00300 |
| Opus 5 | $0.00007 | $0.00150 |
| Sonnet 5 | $0.00003 | $0.00060 |
| Haiku 4.5 | $0.00001 | $0.00030 |
Grade A, and why
doubt-driven-development 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 8d 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
Overview
Every "I'm sure this is fine" is a future incident. This skill applies systematic skepticism to assumptions in requirements, implementations, and integrations before they ship.
When to Use
- When something "seems obvious" but hasn't been verified
- When implementing code that depends on external behavior
- When code review reveals an implicit assumption
- When debugging a "that's impossible" bug
Process
Step 1: List your assumptions
For every non-trivial implementation, write down all the things that must be true for it to work. Make implicit assumptions explicit.
Step 2: Classify by risk
For each assumption: what is the cost if it's wrong? High-cost assumptions must be verified before shipping.
Step 3: Verify high-cost assumptions
How to verify:
- Write a test that fails if the assumption is wrong
- Find the source of truth (spec, documentation)
- Measure it (add a log, run a query)
- Ask someone who knows
Step 4: Make remaining assumptions visible
For assumptions you can't verify before shipping: document them as known assumptions. Future engineers must be able to find them.
Verification Requirements
- All non-trivial assumptions listed
- High-cost assumptions verified before shipping
- Remaining assumptions documented in code
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.
- 8d ago First seen · 42 lines · 14 tokens per session scan A db90ca9fdbce
doubt-driven-development is a skill published in the GitHub repository vignesh2027/AI-AGENT-SKILLS (2 stars, last pushed 10d ago), licensed MIT. It adds 14 tokens to every session and 300 once invoked, about $0.0001 per session on Opus 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
mine-plan-review
Strictly review one implemented repository plan against AGENTS.md, architecture, the immutable plan, implementation commits, real runtime behavior, verification evidence, and downstream contracts. Use when the user invokes the host-specific mine-plan-review skill with a plan path, asks whether a plan can be accepted…
review-checklist
A structured checklist for reviewing work and bringing the review to a clear close. It covers preparing evidence, freezing the checklist, updating status, and resolving remaining items.
audit-tech-design
A review checklist for technical designs, covering architecture, technology choices, and the plan for implementing a system or feature.
expert-output-quality
A quality-checking guide for expert-level code, documentation, examples, test fixtures, quick starts, technical plans, and reports. It distinguishes recommended production paths from framework features, test-only boundaries, and unsupported patterns.
audit-execution-guide
An execution-review guide for checking coding work in prioritized batches and targeted subsets. Its excerpt does not provide more detail about the checks it performs.
audit-project
An engineering review skill covering twelve project-audit areas. The listed areas include code quality, project structure, dependency safety, and resource leaks.