end-phase

end-phase is a skill for Claude Code from alicicek/tale-mode. It costs 82 tokens per session (629 once invoked), scanned A, original, MIT.

An explicit off-switch for a Tale Mode build phase, which is a workflow that enforces committed checks before stopping.

In plain words
What is it for?
Clearing Tale Mode phase markers after the user explicitly asks to end or disarm the phase loop.
Why use it?
It removes the phase marker when the user has decided the phase is finished, abandoned, or being re-scoped.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the tale-mode plugin — 6 skills, 2 commands, 1 agent shipped together

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.

agentmods
npx agentmods add skills/alicicek/tale-mode/end-phase
Any agent
npx skills add alicicek/tale-mode --skill end-phase
Clone the repo
git clone --depth 1 https://github.com/alicicek/tale-mode

Made for: Claude Code.

Or install tale-mode, the plugin that ships this one along with the rest of its 6 skills, 2 commands, 1 agent.

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 end-phase

README.md
[![agentmods](https://agentmods.dev/badge/skills/alicicek/tale-mode/end-phase.svg)](https://agentmods.dev/skills/alicicek/tale-mode/end-phase)
Your own site
<a href="https://agentmods.dev/skills/alicicek/tale-mode/end-phase"><img src="https://agentmods.dev/badge/skills/alicicek/tale-mode/end-phase.svg" alt="Measured on agentmods" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 629 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00082 $0.00629
Opus 5 $0.00041 $0.00315
Sonnet 5 $0.00016 $0.00126
Haiku 4.5 $0.00008 $0.00063

Measured 6d ago against content hash 96c3c0721d2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

end-phase 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 6d 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.

plugins/tale-mode/skills/end-phase/SKILL.md · 46 lines

What it actually says

End a phase

A /tale-mode:kickoff-phase (or the kickoff-phase skill) arms committed-gate enforcement by writing a session-scoped marker <project>/.claude/tale-mode.phase.<session-id>.json. Normally you never need this skill — the marker dies with the session (/clear orphans it and a ~24h reap removes strays), and hitting max_rounds disarms it. This skill is the explicit, immediate off-switch: the user has decided the phase is over (shipped, abandoned, or being re-scoped) and wants enforcement gone now, mid-session.

Guardrail first: if a committed gate is currently RED and the user hasn't clearly said to stop the phase, do NOT reach for this skill — driving the gate to green (or pausing via needs_user in the marker) is the designed path. Ending a phase to silence a failing gate is the exact band-aid tale-mode exists to prevent; confirm intent before clearing.

To end the phase, from the project root:

ls .claude/tale-mode.phase.*.json 2>/dev/null   # see what's armed (may be none)
rm -f .claude/tale-mode.phase.*.json            # clear it/them

Notes, so you report accurately:

  • You can't know your own session id, so clear all markers matching the glob. That's safe: any non-current markers belong to crashed/old sessions (each session only ever reads its own), and a marker only enables enforcement of gates the user already content-hash-trusted — clearing markers just returns every session in this repo to normal, un-enforced behavior.
  • This also removes a not-yet-adopted .claude/tale-mode.phase.pending.json (the cross-platform kickoff arming file), un-arming a kickoff that hasn't had its first Stop event yet.
  • This does not touch an ad-hoc goal-file (.claude/active-goal*.json) — that's the separate agent-armed loop. Mention it if one exists; only delete it when the user asks for that too (and explain why, per the goal-loop's own rules).
  • No markers found → say so; nothing was armed, nothing to end.
  • Confirm the result to the user: what was removed, and that the committed gates are now inert until the next kickoff.
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. 6d ago First seen · 46 lines · 82 tokens per session scan A 96c3c0721d2d

Subscribe to this mod's changes

end-phase is a skill published in the GitHub repository alicicek/tale-mode (36 stars, last pushed 2mo ago), licensed MIT. It adds 82 tokens to every session and 629 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 2026-08-30.

Related

Other skills, from other repositories

recipe-reverse-engineer

Generate PRD and Design Docs from existing codebase through discovery, generation, verification, and review workflow.

shinpr/claude-code-workflows · 26 tokens

recipe-front-review

Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.

shinpr/claude-code-workflows · 29 tokens

new-skill

Scaffold a new brooks-lint analysis skill so it passes npm run validate and npm run evals on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (sequentially numbered steps), then appends…

hyhmrright/brooks-lint · 145 tokens

brooks-sweep

Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…

hyhmrright/brooks-lint · 178 tokens

brooks-test

Test quality review drawing on twelve classic engineering books — with primary focus on xUnit Test Patterns, The Art of Unit Testing, How Google Tests Software, and Working Effectively with Legacy Code — that diagnoses structural problems in an existing test suite: brittleness, mock abuse, coverage illusions, slow…

hyhmrright/brooks-lint · 161 tokens

recipe-add-integration-tests

Add integration/E2E tests to existing codebase using Design Docs.

shinpr/claude-code-workflows · 19 tokens