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 aleksbuss/orchestra --skill doubt-driven-developmentgit clone --depth 1 https://github.com/aleksbuss/orchestraWrote 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/aleksbuss/orchestra/doubt-driven-development)<a href="https://agentmods.dev/skills/aleksbuss/orchestra/doubt-driven-development"><img src="https://agentmods.dev/badge/skills/aleksbuss/orchestra/doubt-driven-development/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/aleksbuss/orchestra/doubt-driven-development"><img src="https://agentmods.dev/badge/skills/aleksbuss/orchestra/doubt-driven-development.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 | $0.00067 | $0.03585 |
| Opus 5.5 | $0.00027 | $0.01434 |
| Sonnet 5.5 | $0.00013 | $0.00717 |
| Haiku 4.5 | $0.00007 | $0.00359 |
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 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.
This is a copy
100% identical to doubt-driven-development — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Doubt-Driven Development
Overview
A confident answer is not a correct one. Long sessions accumulate context that quietly turns assumptions into "facts" without anyone noticing. Doubt-driven development is the discipline of materializing a fresh-context reviewer — biased to disprove, not approve — before any non-trivial output stands.
This is not /review. /review is a verdict on a finished artifact. This is an in-flight posture: non-trivial decisions get cross-examined while course-correction is still cheap.
When to Use
A decision is non-trivial when at least one of these is true:
- It introduces or modifies branching logic
- It crosses a module or service boundary
- It asserts a property the type system or compiler cannot verify (thread safety, idempotence, ordering, invariants)
- Its correctness depends on context the future reader cannot see
- Its blast radius is irreversible (production deploy, data migration, public API change)
Apply the skill when:
- About to make an architectural decision under uncertainty
- About to commit non-trivial code
- About to claim a non-obvious fact ("this is safe", "this scales", "this matches the spec")
- Working in code you don't fully understand
When NOT to use:
- Mechanical operations (renaming, formatting, file moves)
- Following a clear, unambiguous user instruction
- Reading or summarizing existing code
- One-line changes with obvious correctness
- Pure tooling operations (running tests, listing files)
- The user has explicitly asked for speed over verification
If you doubt every keystroke, you ship nothing. The skill applies only to non-trivial decisions as defined above.
Loading Constraints
This skill is designed for the main-session orchestrator, where Step 3 (DOUBT, detailed below) can spawn a fresh-context reviewer.
- Do NOT add this skill to a persona's
skills:frontmatter. A persona that follows Step 3 would spawn another persona — the orchestration anti-pattern explicitly forbidden byreferences/orchestration-patterns.md("personas do not invoke other personas"). - If you find yourself applying this skill from inside a subagent context (where Claude Code prevents nested subagent spawn): the preferred path is to surface to the user that doubt-driven cannot run nested and let the main session handle it. As a last resort only, a degraded self-questioning fallback exists — rewrite ARTIFACT + CONTRACT as a fresh self-prompt with a hard mental separator from your prior reasoning, and walk Steps 1–5. This is not fresh-context review (you carry your own context with you), so flag the result as degraded and prefer escalation whenever the user is reachable.
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 · 244 lines · 67 tokens per session scan A 59aef769adea
doubt-driven-development is a skill published in the GitHub repository aleksbuss/orchestra (2 stars, last pushed 14d ago), licensed MIT. It adds 67 tokens to every session and 3,585 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to doubt-driven-development, differing in 6 lines, and is treated as a copy.
Other skills, from other repositories
code-review
Revisão holística pré-commit (estilo PR Review). Valida o diff contra as 3 memórias vivas, a spec da task e Clean Code, em paralelo ao QA/Security (fan-out); a evidência de teste é exigida no join. Executada pelo Tech Lead; veredito escrito em review.md.
guard
Automatiza ADRs (Architecture Decision Records) e verifica conformidade arquitetural do diff. Use para "criar ADR", "validar arquitetura" ou "checar padrões".
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
architecture-review
Review a diff or a branch range for the architecture drift lint cannot see. Run the scoped linters and the parity check first. Then work a checklist keyed to dev/docs/ARCHITECTURE.md: new Api operations or contract shapes without a ruling, new or cut edges between modules, authorization or audit hand-rolled beside the…
meta-codereview-current-diff
Read the current uncommitted diff, run three independent reviewers (safety + tests-coverage + style) in parallel, then arbitrate a single BLOCK / BLOCKWITHOVERRIDE / PASSWITHNOTES verdict. Use before commit when you want a multi-perspective second-opinion instead of a single-reviewer agent loop.
prs-awaiting-maintainer
List open pull requests where the ball is in the maintainer's court: CI is green and the PR is ready for a maintainer to review, re-review, or merge. Use when the user wants to see PRs awaiting maintainer action.