agentmods.dev

cancel-jeffy

cancel-jeffy is a skill for Claude Code from lenamonj/jeffy-loop. It costs 27 tokens per session (366 once invoked), scanned A, original, MIT.

A command that stops the active Jeffy improvement loop in a project. Jeffy is an automated work cycle that continues a task through repeated sessions.

In plain words
What is it for?
Use it to remove the loop's state files, report the active session details, and confirm that the loop has been cancelled.
Why use it?
It lets you end that cycle without removing the project's planning and journal files.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions Claude Code.

not rated 13repo +2 changed 1mo ago A scan 27 tokens original MIT

Good fit Use it to remove the loop's state files, report the active session details, and confirm that the loop has been cancelled.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lenamonj/jeffy-loop/cancel-jeffy
View source ↗ lenamonj/jeffy-loop
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 lenamonj/jeffy-loop --skill cancel-jeffy
Clone the repo
git clone --depth 1 https://github.com/lenamonj/jeffy-loop

Made for: Claude Code.

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 cancel-jeffy

README.md
[![agentmods](https://agentmods.dev/badge/skills/lenamonj/jeffy-loop/cancel-jeffy/github.svg)](https://agentmods.dev/skills/lenamonj/jeffy-loop/cancel-jeffy)
Your own site
<a href="https://agentmods.dev/skills/lenamonj/jeffy-loop/cancel-jeffy"><img src="https://agentmods.dev/badge/skills/lenamonj/jeffy-loop/cancel-jeffy/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 cancel-jeffy

Your own site · 80×15
<a href="https://agentmods.dev/skills/lenamonj/jeffy-loop/cancel-jeffy"><img src="https://agentmods.dev/badge/skills/lenamonj/jeffy-loop/cancel-jeffy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 366 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00027 $0.00366
Opus 5.5 $0.00011 $0.00146
Sonnet 5.5 $0.00005 $0.00073
Haiku 4.5 $0.00003 $0.00037

Measured 1mo ago against content hash f82e0a42afbf, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cancel-jeffy 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.

skills/cancel-jeffy/SKILL.md · 16 lines

What it actually says

Cancel Jeffy

Stop the Jeffy loop in this project by removing the loop state file the Stop hook reads.

  1. Project root is the directory Claude Code was started in, not wherever the shell currently sits: the Bash tool's cwd persists across calls and may have drifted into a subdirectory that holds its own orphaned state file from another session. Always check state files with absolute paths anchored at the project root, never bare relative ones.
  2. Check <project-root>/.claude/jeffy-loop.local.md. If it exists, read its frontmatter and report its session_id, iteration, and started_at, then delete the file, and <project-root>/.claude/jeffy-loop.local.md.refused beside it when that sidecar exists (the Stop hook writes it after refusing a state file whose frontmatter opener is not exactly ---), and confirm the loop is cancelled. Once the file is gone the Stop hook lets the session end normally.
  3. Also check <project-root>/.claude/ralph-loop.local.md: it belongs to the ralph-loop plugin's engine or a pre-2.0 Jeffy. If it exists, report the same frontmatter fields and delete it too, so no legacy loop keeps re-feeding.
  4. If neither file exists, report that no Jeffy loop is active in this project and stop.
  5. Remind the user that PLAN.md, BACKLOG.md, and JOURNAL.md are untouched: the loop picks up where it left off the next time they run /jeffy.
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. 1mo ago Changed f82e0a42afbf
  2. 2mo ago First seen · 16 lines · 27 tokens per session scan A 8b1fff4032b3

Subscribe to this mod's changes

cancel-jeffy is a skill published in the GitHub repository lenamonj/jeffy-loop (13 stars, last pushed 2d ago), licensed MIT. It adds 27 tokens to every session and 366 once invoked, about $0.0001 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.

Claude Codeai-agentsautonomous-agentclaudecode-qualitydeveloper-tools
Related

cancel-jeffy compared with skills from other repositories

cancel-jeffy next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
cancel-jeffylenamonj/jeffy-loopSkill132d agoMITA27Claude Code
research-refinewanshuiyin/Auto-claude-code-research-in-sleepSkill19k2d agoMITA101Claude Code
paper-illustrationwanshuiyin/Auto-claude-code-research-in-sleepSkill19k2d agoMITA67Claude Code
rebuttalwanshuiyin/Auto-claude-code-research-in-sleepSkill19k2d agoMITA73Claude Code
slides-polishwanshuiyin/Auto-claude-code-research-in-sleepSkill19k2d agoMITA136Claude Code
research-implement-featurewanshuiyin/Auto-claude-code-research-in-sleepSkill19k2d agoMITA120Claude Code
research-wikiwanshuiyin/Auto-claude-code-research-in-sleepSkill19k2d agoMITA73Claude Code