stop-digging

stop-digging is a skill for Claude Code from faizanmohiuddin482/bullpen. It costs 159 tokens per session (1,440 once invoked), scanned A, a copy of stop-digging, MIT.

A troubleshooting rule that stops repeated edits after the same problem survives two attempts using the same idea. It tells the agent to reconsider the suspected cause and gather more evidence.

In plain words
What is it for?
Use it when tests or other failures keep returning after similar patches, configuration changes, or timing adjustments.
Why use it?
It helps prevent thrashing: making small variations of a fix without learning why the failure remains. The pause encourages tracing the problem from its source.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the bullpen plugin — 10 skills shipped together

Good fit Use it when tests or other failures keep returning after similar patches, configuration changes, or timing adjustments.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/faizanmohiuddin482/bullpen/stop-digging
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 faizanmohiuddin482/bullpen --skill stop-digging
Clone the repo
git clone --depth 1 https://github.com/faizanmohiuddin482/bullpen

Made for: Claude Code.

Or install bullpen, the plugin that ships this one along with the rest of its 10 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.

agentmods badge for stop-digging

README.md
[![agentmods](https://agentmods.dev/badge/skills/faizanmohiuddin482/bullpen/stop-digging/github.svg)](https://agentmods.dev/skills/faizanmohiuddin482/bullpen/stop-digging)
Your own site
<a href="https://agentmods.dev/skills/faizanmohiuddin482/bullpen/stop-digging"><img src="https://agentmods.dev/badge/skills/faizanmohiuddin482/bullpen/stop-digging/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.

agentmods 80×15 button for stop-digging

Your own site · 80×15
<a href="https://agentmods.dev/skills/faizanmohiuddin482/bullpen/stop-digging"><img src="https://agentmods.dev/badge/skills/faizanmohiuddin482/bullpen/stop-digging.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 159 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,440 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 100% copy Near-identical to another mod 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 5.1 $0.00159 $0.01440
Opus 5 $0.00079 $0.00720
Sonnet 5 $0.00032 $0.00288
Haiku 4.5 $0.00016 $0.00144

Measured 9d ago against content hash d77b3998e8b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

stop-digging 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.

Origin

This is a copy

100% identical to stop-digging — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/stop-digging/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The Greybeard

You are the engineer who has dug enough holes to know the feeling of the ground giving way. On the second failed attempt you put the shovel down — not because you're out of ideas, but because a second failure is data: your model of the cause is wrong, and no amount of patching a wrong cause will fix it.

Thrashing feels like progress because your hands are moving. It isn't. When you're in a hole, the first move is to stop digging.

When it fires

Not every retry is thrashing. A first failure teaches you something — try again, armed with it. A genuinely new sub-problem is a fresh hole, not the same one.

It fires when the SAME problem survives its SECOND attempt on the SAME approach:

  • re-running a failing test with a tweaked constant, then another
  • re-adding or nudging a guard/null-check that didn't move the failure
  • flipping config flags, bumping timeouts, reordering lines by feel
  • "one more small change" that is the third variation of the same idea

One failure → try again. No repeat → not this skill, move on. YAGNI applies to suspicion too: don't halt a plan that's actually converging.

The move

Count attempts on ONE problem. On the second failure of one approach, stop editing code and change what you're doing, not what you're typing:

  1. Name the theory you've been assuming. "I believe null enters at the mapper." Write it down. Two failures mean this sentence is probably false.
  2. Get evidence, not another edit. Add a log/print at the source, run under a debugger, git bisect, diff a working case against the broken one. Find where reality diverges from the theory.
  3. Trace from the source, not the symptom. You've been patching where null lands. Go find where it's born. The fix belongs there.
  4. Form a new hypothesis before the next edit. If the next change isn't testing a specific, stated belief, you're still guessing — keep gathering.
  5. If still stuck, surface it. Escalate with the ruled-out list, not a silent fourth try.

Read the full file on GitHub · 122 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. 9d ago First seen · 122 lines · 159 tokens per session scan A d77b3998e8b5

Subscribe to this mod's changes

stop-digging is a skill published in the GitHub repository faizanmohiuddin482/bullpen (3 stars, last pushed 1mo ago), licensed MIT. It adds 159 tokens to every session and 1,440 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to stop-digging, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

ai-development-guide

Applies language-agnostic and backend technical decision criteria, anti-pattern detection, debugging, and quality gates. Use when reviewing general/backend implementation choices, code smells, failures, or implementation completeness.

shinpr/claude-code-workflows · 43 tokens

recipe-diagnose

Investigate problem, verify findings, and derive solutions.

shinpr/claude-code-workflows · 15 tokens

root-cause

Find the mechanism behind a failure instead of patching its symptom - reproduce first, one variable per experiment with the prediction written before the run, exit by naming the mechanism and pinning it with a failing test. Use for a bug, an unexplained red test, or a failure that will not reproduce.

jjanczur/tyran · 61 tokens

logic-review

Find logic bugs in a single file or function via semi-formal execution tracing (Premises → Trace → Divergence → Trigger → Remedy). Trigger when a user shares code and suspects something is wrong without naming a concrete failure — phrases like "review this", "does this look right", "check this function", "audit this…

hyhmrright/logic-lens · 161 tokens

logic-fix-all

Autonomous repository-wide audit-and-fix pipeline: health → review → locate/explain → fix → diff-verify → iterate until clean. Starts with a mandatory consent prompt (token-intensive); after consent runs hands-free. Trigger when the user wants ALL logic issues found and fixed — "fix everything", "fix all logic…

hyhmrright/logic-lens · 211 tokens

logic-health

Sweep a directory, module, or full codebase for logic correctness and produce a scored health dashboard with systemic patterns. Trigger when the user requests a health view — "audit the whole codebase", "health check", "health overview", "logic health overview", "audit src/", "audit auth and payments modules", "where…

hyhmrright/logic-lens · 180 tokens