What is compound-knowledge?

A documentation workflow for recording solved software problems as searchable files. It groups solutions by categories such as build errors, test failures, runtime errors, and security issues.

Use it after resolving a bug or failure to document the context, solution, and ways to prevent it from recurring.

It preserves the cause and fix of a problem so the team can find the answer instead of investigating the same issue again.

compound-knowledge — Skill for Claude Code by JairoTorregrosa

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.

Any agent

npx skills add JairoTorregrosa/jaiskills --skill compound-knowledge

Clone the repo

git clone --depth 1 https://github.com/JairoTorregrosa/jaiskills

Made for: Claude Code.

Or install jaiskills, the plugin that ships this one along with the rest of its 12 skills, 13 commands, 4 agents, 2 hooks, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jairotorregrosa/jaiskills/compound-knowledge/github.svg)](https://agentmods.dev/skills/jairotorregrosa/jaiskills/compound-knowledge)

Your own site

<a href="https://agentmods.dev/skills/jairotorregrosa/jaiskills/compound-knowledge"><img src="https://agentmods.dev/badge/skills/jairotorregrosa/jaiskills/compound-knowledge/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jairotorregrosa/jaiskills/compound-knowledge"><img src="https://agentmods.dev/badge/skills/jairotorregrosa/jaiskills/compound-knowledge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 951 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00075	$0.00951
Opus 5	$0.00037	$0.00476
Sonnet 5	$0.00015	$0.00190
Haiku 4.5	$0.00007	$0.00095

Measured 9d ago against content hash 593822c28739, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

compound-knowledge 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 9d 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/knowledge/compound-knowledge/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Compound Knowledge Skill

Capture a solved problem as searchable documentation so the team never solves the same problem twice.

Only ONE file gets written — the final documentation. All sub-agents return text only.

Filename Convention

docs/solutions/<category>/YYYY-MM-DD-<kebab-description>.md

Example: docs/solutions/runtime-errors/2026-02-13-null-pointer-in-auth-middleware.md

Solution Template

Use the template at solution-template.md for the final file format.

Orchestration: 3 Phases

Phase 1: Parallel Information Gathering (3 sub-agents via Task tool)

Spawn these three sub-agents in parallel using the Task tool. Each receives the conversation context about the solved problem and returns structured text. None of these sub-agents write files.

1a. Context Analyzer

Prompt: Analyze the conversation and codebase context to extract:

Problem type: Which category from the list above best fits
Affected area: Files, modules, or systems involved
Severity: low / medium / high / critical
How detected: How the problem surfaced (test failure, user report, monitoring alert, etc.)
Impact: What was broken or degraded

Return as structured text.

1b. Solution Extractor

Prompt: Analyze the conversation and code changes to extract:

Root cause: Why the problem happened (1-2 paragraphs)
Code references: Specific files and lines involved
What fixed it: The actual changes made (before/after snippets)
Key insight: The non-obvious realization that led to the fix

Return as structured text.

1c. Prevention Strategist

Prompt: Based on the problem and solution, determine:

How to prevent recurrence: Specific practices, checks, or guards
Tests to add: What test cases would catch this in the future
Monitoring: Any alerts or checks that should exist
Related patterns: Similar problems that might exist elsewhere

Read the full file on GitHub · 113 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

references/solution-template.md 1.5 KB

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.

9d ago First seen · 113 lines · 75 tokens per session scan A 593822c28739

Subscribe to this mod's changes

compound-knowledge is a skill published in the GitHub repository JairoTorregrosa/jaiskills (5 stars, last pushed 8d ago), licensed MIT. It adds 75 tokens to every session and 951 once invoked, about $0.0004 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.

Claude Code Debugging Multi-Agent Writing and docs agents plugin skills

python-code-quality

Code quality checks, linting, formatting, and type checking commands for the Agent Framework Python codebase. Use this when running checks, fixing lint errors, or troubleshooting CI failures.

microsoft/agent-framework · 40 tokens

testing-dags

Complex DAG testing workflows with debugging and fixing cycles. Use for multi-step testing requests like "test this dag and fix it if it fails", "test and debug", "run the pipeline and troubleshoot issues". For simple test requests ("test dag", "run dag"), the airflow entrypoint skill handles it directly. This skill…

astronomer/agents · 77 tokens

debugging-dags

Comprehensive DAG failure diagnosis and root-cause analysis with structured investigation and prevention recommendations. Use when deep failure investigation is needed, a DAG fails to import/parse or 'airflow dags list' errors on a file; a task or run is failing and must be diagnosed and fixed; requests like 'why did…

astronomer/agents · 111 tokens

compound-knowledge