Menu

#342 by GitHub stars

lennney/stop-that-shit

Stop That Shit（别再造史了）｜面向 Codex/GPT 场景的多平台 Hook + Skill Guard：拦截 AI coding agent 无需求的哈希、校验和与任务范围膨胀。 A multi-platform Hook + Skill Guard for AI coding agents in Codex/GPT workflows: stop unrequested hashes, checksums, and task-scope creep.

Claude CodeEngineering

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

codex-plugin/skills/stop-that-shit/SKILL.md

Week of Nov 2, 2026 · +12 / −0 lines

Before Instructions only → After Local scripts

17ffc9f51083 → 3929e2df30ac

+ 121 With Codex `change deps=ask`, a supported direct dependency command can produce
+ 122 one native approval question tied to that exact command and its proposed target
+ 123 directory. Choose the explicit allow or deny option in the question. Closing it,
+ 124 leaving it unanswered, or replying with ordinary text does not grant
+ 125 permission. An allow permits one matching retry within ten minutes; the session
+ 126 policy remains `deps=ask`. In a delegated Codex agent, the proposal, answer and
+ 127 one-time runner ticket stay in that agent's child state. The child is evaluated
+ 128 against the latest parent and child contract, and a parent approval cannot be
+ 129 reused by a child. If the host does not provide its child-state API, scoped
+ 130 approval questions and child contract changes are refused; ordinary child
+ 131 clarification and non-approval tools keep their normal path.
+ 132

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 17ffc9f51083

No earlier version was observed for comparison.

Compare on GitHub

codex-plugin/skills/stss/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Instructions only → After Instructions only

17ffc9f51083 → 3929e2df30ac

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 17ffc9f51083

No earlier version was observed for comparison.

Compare on GitHub

skills/stop-that-shit/SKILL.md

Week of Nov 2, 2026 · +12 / −0 lines

Before Instructions only → After Instructions only

17ffc9f51083 → 3929e2df30ac

+ 121 With Codex `change deps=ask`, a supported direct dependency command can produce
+ 122 one native approval question tied to that exact command and its proposed target
+ 123 directory. Choose the explicit allow or deny option in the question. Closing it,
+ 124 leaving it unanswered, or replying with ordinary text does not grant
+ 125 permission. An allow permits one matching retry within ten minutes; the session
+ 126 policy remains `deps=ask`. In a delegated Codex agent, the proposal, answer and
+ 127 one-time runner ticket stay in that agent's child state. The child is evaluated
+ 128 against the latest parent and child contract, and a parent approval cannot be
+ 129 reused by a child. If the host does not provide its child-state API, scoped
+ 130 approval questions and child contract changes are refused; ordinary child
+ 131 clarification and non-approval tools keep their normal path.
+ 132

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 17ffc9f51083

No earlier version was observed for comparison.

Compare on GitHub

skills/stss/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Instructions only → After Instructions only

17ffc9f51083 → 3929e2df30ac

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 17ffc9f51083

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit 3929e2df30ac299a1de25a155d2ac8b3f354952b

git clone --filter=blob:none --no-checkout https://github.com/lennney/stop-that-shit.git .hotskills/lennney-stop-that-shit && git -C .hotskills/lennney-stop-that-shit checkout --detach 3929e2df30ac299a1de25a155d2ac8b3f354952b # Copy each selected skill directory from .hotskills/lennney-stop-that-shit into .claude/skills/<skill-name>/
3.7kGitHub stars
257stars in 7 days
4skills in this repository
96commits in 30 days

Heat

8.4
  • Star growth, last 7 daysAhead of 98% of tracked repositories
  • Star growth, last 24 hoursAhead of 98% of tracked repositories
  • Rank movement, last 7 daysAhead of 92% of tracked repositories
  • Commits, last 30 daysAhead of 94% of tracked repositories
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekAhead of 0% of tracked repositories

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Aug 9, 2026Nov 7, 20263,695

Individual skills in this repository

How it works

stop-that-shit

When your agent uses it

Complete requested work while preventing speculative defenses and scope creep. Use when considering extra hardening, reviewing possible overengineering, resolving repeated verification loops, following explicit task boundaries, or when the user invokes Stop That Shit. Ordinary use of validation, retries, or dependencies alone is not a trigger.

What it loads into context

Frontmatter

70 tokens

Always available to the agent

SKILL.md

1,810 tokens

When the skill is activated

Reference documents

4,285 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. Follow the Stop Ladder
  2. Resolve uncertainty without inventing work
  3. Keep the deliverable focused
  4. Respect the task mode
  5. Finish

Files

  • ../../../.claude-plugin/marketplace.jsonasset457 bytes
  • ../../../.claude-plugin/plugin.jsonasset613 bytes
  • SKILL.mdcore9,037 bytes
  • agents/openai.yamlasset263 bytes
  • ../../../hooks/hooks.jsonasset2,340 bytes
  • ../../../hooks/hooks.jsonasset2,340 bytes
  • ../../../hooks/hooks.jsonasset2,340 bytes
  • ../../../hooks/hooks.jsonasset2,340 bytes
  • ../../../hooks/hooks.jsonasset2,340 bytes
  • ../../../hooks/hooks.jsonasset2,340 bytes
  • ../../../hooks/hooks.jsonasset2,340 bytes
  • ../../../hooks/hooks.jsonasset2,340 bytes
  • ../../../hooks/hooks.jsonasset2,340 bytes
  • ../../../skills/stop-that-shit/SKILL.mddoc9,037 bytes
  • ../../../skills/stop-that-shit/agents/openai.yamlasset263 bytes
  • ../../../skills/stss/SKILL.mddoc4,694 bytes
  • ../../../skills/stss/agents/openai.yamlasset311 bytes
  • ../../../skills/stss/references/examples.mddoc7,597 bytes
Read SKILL.md

# Stop That Shit

Meet the task's responsibilities in full. Let real needs drive complexity.

This Skill is advisory and works without the Guard hooks. It cannot guarantee
model behavior. When the Guard is installed, the same directives also provide
machine-enforced boundaries on supported host action paths.

## Follow the Stop Ladder

Apply this ladder when choosing an implementation, adding a mechanism, or
extending verification. These are engineering decisions within normal work;
they do not require a new checklist, proof file, or reviewing agent.
View the complete source on GitHub

Skills included

  • stop-that-shit
  • stss
  • stop-that-shit
  • stss

Repository facts

License
MIT
Created
Aug 11, 2026
Last pushed
Nov 5, 2026
Forks
76
Open issues
2
Project activity
Active

Rank over the last 12 weeks

Now #342 · best #342 · up 53 in 30 days

  1. #350 on Nov 2
  2. #349 on Nov 3
  3. #346 on Nov 4
  4. #344 on Nov 5
  5. #343 on Nov 6
  6. #342 since Nov 7
79 earlier periods
  1. #897 on Aug 9
  2. #919 on Aug 12
  3. #921 on Aug 13
  4. #895 on Aug 14
  5. #860 on Aug 15
  6. #885 on Aug 16
  7. #890 on Aug 17
  8. #906 on Aug 18
  9. #901 on Aug 19
  10. #884 on Aug 20
  11. #893 on Aug 21
  12. #838 on Aug 22
  13. #888 on Aug 23
  14. #894 on Aug 24
  15. #899 on Aug 25
  16. #881 on Aug 26
  17. #865 on Aug 27
  18. #868 on Aug 28
  19. #720 on Aug 29
  20. #635 on Aug 30
  21. #610 on Aug 31
  22. #559 on Sep 1
  23. #512 on Sep 2
  24. #492 on Sep 3
  25. #468 on Sep 4
  26. #457 on Sep 5
  27. #451 on Sep 6
  28. #445 on Sep 7
  29. #451 on Sep 8
  30. #442 on Sep 9
  31. #437 on Sep 10
  32. #433 on Sep 11
  33. #426 on Sep 12
  34. #424 on Sep 13
  35. #430 on Sep 14
  36. #426 on Sep 15
  37. #428 on Sep 16
  38. #420 on Sep 17
  39. #425 on Sep 18
  40. #414 on Sep 19
  41. #416 on Sep 20
  42. #412 on Sep 21
  43. #415 on Sep 22
  44. #405 on Sep 23
  45. #399 on Sep 24
  46. #396 on Sep 25
  47. #389 on Sep 26
  48. #394 from Sep 27 to Sep 28
  49. #403 on Sep 29
  50. #395 on Sep 30
  51. #391 on Oct 1
  52. #393 on Oct 2
  53. #383 on Oct 3
  54. #378 on Oct 4
  55. #387 from Oct 5 to Oct 6
  56. #391 on Oct 7
  57. #395 on Oct 8
  58. #406 on Oct 9
  59. #394 on Oct 10
  60. #393 on Oct 11
  61. #400 on Oct 12
  62. #394 on Oct 13
  63. #396 on Oct 14
  64. #394 on Oct 15
  65. #395 on Oct 16
  66. #386 on Oct 17
  67. #392 on Oct 18
  68. #393 on Oct 19
  69. #385 on Oct 20
  70. #377 on Oct 21
  71. #367 on Oct 22
  72. #361 on Oct 23
  73. #352 on Oct 24
  74. #365 on Oct 25
  75. #358 on Oct 28
  76. #353 on Oct 29
  77. #355 on Oct 30
  78. #353 on Oct 31
  79. #352 on Nov 1

Before you install

Local scripts

Automated signals, not a guarantee

Checked Nov 5, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 11 notes
  • hooks/hooks.json:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • hooks/hooks.json:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • hooks/hooks.json:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • hooks/hooks.json:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • hooks/hooks.json:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • hooks/hooks.json:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • hooks/hooks.json:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • hooks/hooks.json:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • hooks/hooks.json:1 Plugin-wide analysis incomplete; see repository notes
  • hooks/hooks.json:1 Plugin-wide analysis incomplete; see repository notes
  • hooks/hooks.json:1 Plugin-wide analysis incomplete; see repository notes
  • No broad tool permissions
  • No dangerous shell commands
  • 6 network referencesin 1 file: .claude-plugin/plugin.json:6
  • No hidden or obfuscated text
  • No instruction overrides
  • No executable scripts
  • No access to secrets
  • No requests to vote in Hot
Show all 6 signals by file

.claude-plugin/plugin.json

  • Network accessline 6
    "author": {     "name": "Stop That Shit contributors",     "url": "https://github.com/lennney"
  • Network accessline 7
    "name": "Stop That Shit contributors",     "url": "https://github.com/lennney"   },
  • Network accessline 8
    "url": "https://github.com/lennney"
  • Network accessline 9
    },   "homepage": "https://github.com/lennney/stop-that-shit",   "repository": "https://github.com/lennney/stop-that-shit",
  • Network accessline 10
    "homepage": "https://github.com/lennney/stop-that-shit",
  • Network accessline 11
    "repository": "https://github.com/lennney/stop-that-shit",

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

No combined signals at this commit.

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeNativeManifest .claude-plugin/marketplace.json.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md codex-plugin/skills/stop-that-shit/SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md codex-plugin/skills/stop-that-shit/SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md codex-plugin/skills/stop-that-shit/SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md codex-plugin/skills/stop-that-shit/SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md codex-plugin/skills/stop-that-shit/SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

You might also use

chipfighter/coding-discipline

Workflow-agnostic guardrails for AI coding agents: spec sync + risk-triggered engineering discipline for Claude Code and Codex.

25GitHub stars

KKKKhazix/khazix-skills

数字生命卡兹克开源的 AI Skills 合集 | Agent Skills: leader（帮你定义目标）, neat-freak 洁癖, hv-analysis, khazix-writer & more — Claude Code, Codex & 40+ agents

22kGitHub stars

google/elephant-goldfish-model

Open-source skills for designing and reviewing software with AI agents

13.1kGitHub stars

NVIDIA/skills

Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end.

3.9kGitHub stars

FrancyJGLisboa/agent-skills-platform

Build tested agent skills and govern their lifecycle through a user-defined marketplace: evidence, discovery, updates, rollback, quarantine, and 17-platform distribution.

2.4kGitHub stars

dzhng/skills

Reusable AI agent skills for software factories: explore ideas, write specs, implement, review, and run autonomous research. Works with Claude Code, Codex, and other skill-compati…

1.4kGitHub stars

Explore alternatives and comparisons

Add this badge to your README

It updates every night and links to this page.

lennney/stop-that-shit: #342 on hotskills, 3.7k stars

[![lennney/stop-that-shit on hotskills](https://hotskills.dev/badge/lennney-stop-that-shit.svg)](https://hotskills.dev/skill/lennney-stop-that-shit/)