hindsight-debug

hindsight-debug is a skill for Claude Code, Codex from ShayManor/Hindsight. It costs 54 tokens per session (381 once invoked), scanned A, original, BSD-2-Clause.

A debugging skill that searches a shared collection of previously reported fixes for difficult, environment-dependent errors. It can compare the error and environment with past attempts and record whether a suggested fix worked.

In plain words
What is it for?
Use it for cryptic build errors, CUDA or compiler mismatches, and distributed-training crashes after recording what you tried.
Why use it?
It reduces guesswork when build failures or toolchain errors are too unusual to solve from memory.

Skill for Claude CodeCodex

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/shaymanor/hindsight/hindsight-debug
Any agent
npx skills add ShayManor/Hindsight --skill hindsight-debug
Clone the repo
git clone --depth 1 https://github.com/ShayManor/Hindsight

Made for: Claude Code, Codex.

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 hindsight-debug

README.md
[![agentmods](https://agentmods.dev/badge/skills/shaymanor/hindsight/hindsight-debug.svg)](https://agentmods.dev/skills/shaymanor/hindsight/hindsight-debug)
Your own site
<a href="https://agentmods.dev/skills/shaymanor/hindsight/hindsight-debug"><img src="https://agentmods.dev/badge/skills/shaymanor/hindsight/hindsight-debug.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 381 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 $0.00054 $0.00381
Opus 5 $0.00027 $0.00191
Sonnet 5 $0.00011 $0.00076
Haiku 4.5 $0.00005 $0.00038

Measured 4d ago against content hash 99863b1d0837, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hindsight-debug 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/hindsight-debug/SKILL.md · 21 lines

What it actually says

Debugging with Hindsight

When an error resists your parametric knowledge, query the shared corpus before guessing.

  1. Search. Call search_error with:
    • trace: the full stack trace / multi-line error, verbatim.
    • message: the headline error (e.g. ImportError: undefined symbol).
    • attempt_summary: one sentence on what you were doing ("Tried to build flash-attention 2.3.6 on Ubuntu 22.04 with torch 2.1 + CUDA 12.1").
    • env: {cuda, os, arch, packages} when known — this conditions and ranks results.
  2. Read the top results. Each carries why (matched frames, env match, and attempts/successes/success_rate) plus source attribution. Prefer solutions with a higher success_rate.
  3. Get the full record. Call get_solution(id) for the chosen result — it includes solution_body, solution_code, and the exact repro_script.
  4. Try the fix.
  5. Always report back. Call report_attempt(id, worked) with worked=true or worked=false. Failures are the most valuable signal — they tell the commons which popular fixes do not actually work. Add notes explaining what differed.

Attribution: results may be licensed CC-BY-SA (Stack Overflow) or MIT. Preserve source.author/source.url if you quote a solution.

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 · 21 lines · 54 tokens per session scan A 99863b1d0837

Subscribe to this mod's changes

hindsight-debug is a skill published in the GitHub repository ShayManor/Hindsight (2 stars, last pushed 16d ago), licensed BSD-2-Clause. It adds 54 tokens to every session and 381 once invoked, about $0.0003 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