What is recoge-tu-tiradero?

A cleanup checklist for removing temporary residue left by debugging or experiments before presenting the final work.

Use it after debugging or experimentation and before collecting final evidence, sharing the result, or handing it to someone else.

It removes traces, scratch files, temporary flags, and abandoned dependencies that helped investigate one incident but do not help maintain the solution.

recoge-tu-tiradero — Skill for Claude Code by mcasillas17

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 mcasillas17/mexican-mom --skill recoge-tu-tiradero

Clone the repo

git clone --depth 1 https://github.com/mcasillas17/mexican-mom

Made for: Claude Code.

Or install mexican-mom, the plugin that ships this one along with the rest of its 24 skills.

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/mcasillas17/mexican-mom/recoge-tu-tiradero/github.svg)](https://agentmods.dev/skills/mcasillas17/mexican-mom/recoge-tu-tiradero)

Your own site

<a href="https://agentmods.dev/skills/mcasillas17/mexican-mom/recoge-tu-tiradero"><img src="https://agentmods.dev/badge/skills/mcasillas17/mexican-mom/recoge-tu-tiradero/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/mcasillas17/mexican-mom/recoge-tu-tiradero"><img src="https://agentmods.dev/badge/skills/mcasillas17/mexican-mom/recoge-tu-tiradero.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,363 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	$0.00077	$0.01363
Opus 5	$0.00039	$0.00681
Sonnet 5	$0.00015	$0.00273
Haiku 4.5	$0.00008	$0.00136

Measured 12d ago against content hash 01ee61f04059, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

recoge-tu-tiradero 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 12d 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/recoge-tu-tiradero/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

A ver si ya recoges tu tiradero

The bug is fixed. Everything you knocked over finding it is still on the floor.

Rule

One test governs every line you added:

KEEP anything that helps the next person diagnose the same class of failure. CUT anything that only helped you diagnose this instance.

Apply it to each added line individually. "I'll leave it, it's harmless" is not a verdict; neither is "I'll delete the whole area to be safe."

Scope: only your residue, from this work. You may remove what you added and restore what you loosened. You may not delete pre-existing code, unrelated TODOs, someone else's commented-out block, a test you did not write, or anything that was in the tree before you started. Removing another person's work under cover of cleanup is worse than the mess — the mess is visible, and that is not.

Procedure

Diff your own changes. Get the full diff of this work against its starting point. Cleanup you do from memory misses the file you touched an hour ago.

Classify every added line by the test above. Most rows are already decided:

What you added	Verdict	Why
A test written while debugging	KEEP	It now guards the class
A helper extracted during the fix	KEEP	It is part of the solution
A structured log line that would diagnose this class in production	KEEP	The next person gets it for free
Trace logging added to find the bug	CUT	It found this instance
`console.log("here 1")` and friends	CUT	It never helped anyone but you
A commented-out earlier attempt	CUT	Git has it
A loosened timeout, retry count, or threshold	CUT and restore	It hides the class
A disabled check, assertion, or lint rule	CUT and restore	Same
`.only` or `.skip` left in a test	CUT	See below
A temporary flag or env toggle	CUT, and remove it from the docs and examples too
A debug or verbose setting switched on	CUT, restore the default
A scratch script, throwaway fixture, or stray output file	CUT	Not part of the solution
A dependency added then abandoned	CUT from the manifest and the lockfile	A lockfile entry is a real install

Read the full file on GitHub · 107 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.

12d ago First seen · 107 lines · 77 tokens per session scan A 01ee61f04059

Subscribe to this mod's changes

recoge-tu-tiradero is a skill published in the GitHub repository mcasillas17/mexican-mom (2 stars, last pushed 1mo ago), licensed MIT. It adds 77 tokens to every session and 1,363 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 agent-skills ai-tools anthropic claude-code-plugin claude-skills

shipkit-feedback-bug

Process user feedback into investigated bug specs with root cause analysis. Triggers: 'triage feedback', 'process bug reports', 'user testing feedback'.

stefan-stepzero/shipkit · 36 tokens

shipkit-codebase-audit

Audit a codebase for dead code, orphaned modules, unused dependencies, and unwired seams. Quick tier runs knip-class checks ephemerally (no repo mutation); deep and exhaustive tiers add intent↔code reconciliation. Portable to any repo, including ones with no tooling installed.

stefan-stepzero/shipkit · 65 tokens

investigate

Deep investigation of bugs, performance issues, or unexpected behavior. TRIGGER THIS SKILL when users report bugs, errors, performance regressions, unexpected behavior, or ask to investigate, debug, diagnose, or find the root cause of any issue — whether they say "why is this broken", "investigate this bug", "find the…

christyjacob4/claude-tricks · 118 tokens

debug

Debug and fix failing tests or errors.

christyjacob4/claude-tricks · 9 tokens

dead-code

Identify unused code (functions, imports, exports, variables, types, classes) and propose cleanup. Use this skill when the user says "find dead code", "unused code", "clean up unused", "code hygiene", "find unused imports", "what can I delete", or any variation of wanting to identify and remove code that is no longer…

lukaskellerstein/claude-my-marketplace · 75 tokens

question

Answer a question about how things are right now — this codebase, its history, its behavior, a library, an error. Investigates and answers with evidence. Changes nothing, ever.

lukaskellerstein/claude-my-marketplace · 40 tokens