session-doubt

session-doubt is a skill for Claude Code, Codex from ao92265/claude-code-playbook. It costs 131 tokens per session (575 once invoked), scanned A, original, MIT.

A guided end-of-session review that lists uncertainties before an agent says substantial work is finished. It also asks what important fact the user may be overlooking.

In plain words
What is it for?
Use it before claiming meaningful work is done to identify weak spots, investigate important doubts, and surface the biggest potential blind spot.
Why use it?
It separates reflective doubt-checking from running tests, helping expose assumptions or risks that ordinary verification may miss.

Skill for Claude CodeCodex

Part of the playbook plugin — 49 skills, 4 hooks shipped together

Install

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.

agentmods
npx agentmods add skills/ao92265/claude-code-playbook/session-doubt
Any agent
npx skills add ao92265/claude-code-playbook --skill session-doubt
Clone the repo
git clone --depth 1 https://github.com/ao92265/claude-code-playbook

Made for: Claude Code, Codex.

Or install playbook, the plugin that ships this one along with the rest of its 49 skills, 4 hooks.

Wrote 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.

agentmods badge for session-doubt

README.md
[![agentmods](https://agentmods.dev/badge/skills/ao92265/claude-code-playbook/session-doubt.svg)](https://agentmods.dev/skills/ao92265/claude-code-playbook/session-doubt)
Your own site
<a href="https://agentmods.dev/skills/ao92265/claude-code-playbook/session-doubt"><img src="https://agentmods.dev/badge/skills/ao92265/claude-code-playbook/session-doubt.svg" alt="Measured on agentmods" height="20"></a>
Per session 131 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 575 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00131 $0.00575
Opus 5 $0.00066 $0.00287
Sonnet 5 $0.00026 $0.00115
Haiku 4.5 $0.00013 $0.00057

Measured 4d ago against content hash 6bffd9881bac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

session-doubt 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.

skills/session-doubt/SKILL.md · 44 lines

What it actually says

session-doubt

Reflective close-out for substantive work. Two questions, asked in order. Source: end-of-session technique (Sam Altman's Q1 + a Claude-suggested Q2) — "1 in 4 times it surfaces a huge deal."

Run AFTER the work is otherwise complete (and ideally after /done / verification-before-completion has run). This is reflection, not test execution — the two are complementary, not substitutes.

Q1 — Least confident

Ask yourself, honestly and without flattering the work:

What am I least confident about right now? Enumerate everything.

  • List every item, not a curated top-3. Aim for 5–8. Include things that feel minor.
  • For each: one line stating the doubt + why.
  • Then root-cause the real ones: pick the items where being wrong would actually matter and investigate each exhaustively (read the code, run the check, trace the path) until you understand the root cause — do not stop at restating the doubt.
  • Be specific. "Error handling might be incomplete" is useless. "If the upload retries after a 413, we double-charge because the idempotency key is regenerated per-attempt — unverified" is useful.

Q2 — Biggest blind spot

Then ask:

What is the biggest thing the user does not realize about this situation right now?

  • One thing. The single highest-leverage reframe, risk, or connection the user is most likely missing.
  • It should change a decision, not just inform. Prefer the insight that contradicts or reframes something the user (or you) already assumed.

Output

**Q1 — least confident (root-caused):**
1. <doubt> — <why> → <root-cause finding or "investigated: benign because …">
2. ...

**Q2 — biggest blind spot:**
<the one reframe, and what decision it changes>

Keep it tight. No reassurance padding. If genuinely nothing is uncertain, say so plainly — do not manufacture doubt to fill the list.

Changes

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.

  1. 4d ago First seen · 44 lines · 131 tokens per session scan A 6bffd9881bac

Subscribe to this mod's changes

session-doubt is a skill published in the GitHub repository ao92265/claude-code-playbook (10 stars, last pushed 18d ago), licensed MIT. It adds 131 tokens to every session and 575 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens