loom-debugging

A step-by-step method for finding and fixing software bugs, failed tests, data problems, and performance issues. It focuses on reproducing a failure, narrowing it down, identifying its root cause, and checking the fix.

In plain words
What is it for?
Investigating stack traces, flaky tests, regressions, crashes, data-quality issues, slow systems, and failures that occur in continuous integration but not on a developer’s machine.
Why use it?
It helps prevent symptom-patching, where a change hides the visible error but leaves the underlying problem in place.

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/cosmix/loom/loom-debugging
Any agent
npx skills add cosmix/loom --skill loom-debugging
Clone the repo
git clone --depth 1 https://github.com/cosmix/loom

Made for: Claude Code, Codex.

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,365 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00057 $0.03365
Opus 5 $0.00028 $0.01682
Sonnet 5 $0.00011 $0.00673
Haiku 4.5 $0.00006 $0.00336

Measured 2d ago against content hash 75b2248e8b1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

loom-debugging scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

tcpdump -i any port 8080 # wire-level; curl -v for HTTP
skills/loom-debugging/SKILL.md · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debugging

Overview

Find the true cause of a defect and prevent its recurrence — across app code, tests, data pipelines, ML, and infra. The failure mode to avoid is symptom-patching: changing code until the symptom disappears without understanding why, which moves the bug rather than fixing it.

The Root-Cause Loop

Run this loop; don't skip steps. Most wasted time comes from hypothesizing before reproducing, or fixing before localizing.

  1. Reproduce — deterministically. If you can't reproduce it, you can't verify a fix. Capture exact inputs, env, versions, and the full error/stack. For intermittent bugs, first make it more frequent (loop it, add load, shrink timeouts) before anything else.
  2. Minimize — shrink to the smallest input/code that still fails. Delete half, re-run, repeat (delta-debugging). A 5-line repro localizes faster than a 5000-line one and often reveals the cause outright.
  3. Localize — bound where it happens before asking why. Bisect in space (comment out / binary-search modules) and in time (git bisect). Read the stack trace top frame first, then the first frame in your code.
  4. Hypothesize — state a specific, falsifiable cause ("X is null because Y returns None when Z"). Vague hypotheses ("something with async") aren't testable.
  5. Test the hypothesis — one variable at a time; change something that should confirm/refute it. If the experiment can't distinguish two causes, design a better one.
  6. Fix — the root cause, minimally. Verify the repro now passes AND that you understand why the fix works (else you may have masked it).
  7. Prevent — add a regression test that fails without the fix. No regression test = the bug is not done. Then generalize: are there sibling instances of the same class elsewhere?

Core Discipline

  • Reproduce before fixing. Never "fix" what you can't observe failing.
  • Read the error fully — message, type, and every stack frame. The answer is often literally in it (wrong frame, unexpected value, swallowed cause).
  • Check recent changes. Most new failures are recently introduced → git log, git bisect.
  • Question your assumptions. The bug lives in what you're sure is correct. Verify it (print it, assert it) rather than believing it.
  • Preserve evidence. Save the failing input, logs, core dump, and seed before you start mutating code.

Read the full file on GitHub · 232 lines

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. 2d ago First seen · 232 lines · 57 tokens per session scan A 75b2248e8b1e

Subscribe to this mod's changes

loom-debugging is a skill published in the GitHub repository cosmix/loom (54 stars, last pushed 3d ago), licensed MIT. It adds 57 tokens to every session and 3,365 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

Agent Design Principles

A checklist for designing agent personas, skills, and multi-agent pipelines that stay reliable as they grow — grounded in the 12-factor-agents principles.

niels-emmer/myace · 34 tokens

workers-best-practices

Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from…

cloudflare/skills · 72 tokens

find-journalists

Build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. Uses the newsjack CLI (preferred) or the medialyst MCP for news search and journalist enrichment, and falls back to a best-effort local mode with no verified contacts; the agent owns how returned data is organized.

elvisun/newsjack · 69 tokens

story-origin-check

Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.

elvisun/newsjack · 40 tokens

annotating-task-lineage

Annotate Airflow tasks with data lineage using inlets and outlets. Use when the user wants to add lineage metadata to tasks, specify input/output datasets, or enable lineage tracking for operators without built-in OpenLineage extraction.

astronomer/agents · 51 tokens

relevance-coarse-filter

Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.

elvisun/newsjack · 57 tokens