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 normful/picadillo --skill mulchgit clone --depth 1 https://github.com/normful/picadilloWrote 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/normful/picadillo/mulch)<a href="https://agentmods.dev/skills/normful/picadillo/mulch"><img src="https://agentmods.dev/badge/skills/normful/picadillo/mulch/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/normful/picadillo/mulch"><img src="https://agentmods.dev/badge/skills/normful/picadillo/mulch.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 | $0.00042 | $0.01208 |
| Opus 5.5 | $0.00017 | $0.00483 |
| Sonnet 5.5 | $0.00008 | $0.00242 |
| Haiku 4.5 | $0.00004 | $0.00121 |
Grade A, and why
mulch 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.
How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mulch Usage
Mulch captures project learnings as structured "records" organized by domain. Each domain represents a category of knowledge:
| Domain | Description |
|---|---|
purpose |
Why the project exists |
identity |
Brand, naming, tone |
public-interface |
APIs, CLI, UI surfaces |
internal-structure |
Code organization |
dependencies |
External libraries |
data |
Database, schemas, models |
configuration |
Env vars, settings |
observability |
Logging, metrics, tracing |
glossary |
Domain-specific terminology |
When to Run Commands
1. At Session Start
Load all project expertise into your context:
mulch prime # load all project learnings
mulch prime --files src/foo.ts # load only records relevant to specific files
This gives you awareness of existing patterns, decisions, and conventions before you start working.
2. While Working
Record insights as you discover them:
# Create a new domain if needed
mulch add purpose
# Record different types of learnings
mulch record <domain> --type pattern --name "Auth Pattern" --description "Use middleware for auth checks before route handlers"
mulch record <domain> --type failure --name "Missing Validation" --description "Form field not validated on client" --resolution "Add Zod schema validation"
mulch record <domain> --type decision --title "Chose PostgreSQL" --rationale "Needed relational queries and ACID compliance"
mulch record <domain> --type convention --content "API routes go in src/routes/"
mulch record <domain> --type reference --name "Error Handling" --description "See docs/error patterns"
mulch record <domain> --type guide --name "Setup Guide" --description "Run npm install then npm run dev"
# Add evidence, files, tags
mulch record <domain> --type pattern --name "..." --description "..." --evidence-commit abc123
mulch record <domain> --type pattern --name "..." --description "..." --evidence-bead fix-42 # link to bd issue
mulch record <domain> --type pattern --name "..." --description "..." --files "src/auth.ts,src/middleware.ts"
mulch record <domain> --type pattern --name "..." --description "..." --tags "security,auth"
# Link related records
mulch record <domain> --type pattern --name "..." --description "..." --relates-to mx-abc123
mulch record <domain> --type pattern --name "..." --description "..." --supersedes mx-old123
# Batch record from JSON file
mulch record <domain> --batch records.json
mulch record <domain> --batch records.json --dry-run # preview first
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 · 149 lines · 42 tokens per session scan A 9eaa4e5ea596
mulch is a skill published in the GitHub repository normful/picadillo (10 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 1,208 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
session-search
Search and verify Joel's Pi, Claude, Codex, Cursor, Grok, and OpenCode session history. Use when asked to recover prior context, find exact transcript evidence, inspect session receipts, continue old work, or verify capture health. Prefer flowing recall before raw transcript search when the question is about prior…
session-capture
Historical pointer for the retired Codex-to-Central capture plugin. Use only to inspect legacy state during migration; current capture belongs to the joelclaw flowing-memory host adapter.
codebase-memory
Use the codebase knowledge graph for structural code queries. Triggers on: explore the codebase, understand the architecture, what functions exist, show me the structure, who calls this function, what does X call, trace the call chain, find callers of, show dependencies, impact analysis, dead code, unused functions…
surf
Control Chrome browser via CLI for testing, automation, and debugging. Use when the user needs browser automation, screenshots, form filling, page inspection, network/CPU emulation, DevTools streaming, or AI queries via ChatGPT/Gemini/Perplexity/Grok/AI Studio.
prose-review
Review prose written for others (e.g., user-facing documentation, prompts for other LLMs, reports, plans, inline comments, docstrings) for local jargon leakage, orphaned references, missing grounding, and audience or genre mismatch. Always run on prose you produce or materially edit, except for routine conversational…
text-search
Search indexed text corpora with qmd. For indexed content, prefer qmd over grep.