kill-initiative

kill-initiative is a skill for Claude Code from tomzx/agents. It costs 33 tokens per session (578 once invoked), scanned A, original, MIT.

A process for formally stopping a product initiative and recording why it ended. It also updates the roadmap, frees team capacity, informs stakeholders, and captures lessons learned.

In plain words
What is it for?
Use it after evidence shows an initiative should stop, such as a failed experiment, weak customer need, poor economics, or a broken safety condition.
Why use it?
It prevents failed or low-value work from quietly consuming time and allows the team to learn from the decision.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: positional $N argument.

Good fit Use it after evidence shows an initiative should stop, such as a failed experiment, weak customer need, poor economics, or a broken safety condition.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tomzx/agents/kill-initiative
View source ↗ tomzx/agents
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 tomzx/agents --skill kill-initiative
Clone the repo
git clone --depth 1 https://github.com/tomzx/agents

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 kill-initiative

README.md
[![agentmods](https://agentmods.dev/badge/skills/tomzx/agents/kill-initiative/github.svg)](https://agentmods.dev/skills/tomzx/agents/kill-initiative)
Your own site
<a href="https://agentmods.dev/skills/tomzx/agents/kill-initiative"><img src="https://agentmods.dev/badge/skills/tomzx/agents/kill-initiative/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 kill-initiative

Your own site · 80×15
<a href="https://agentmods.dev/skills/tomzx/agents/kill-initiative"><img src="https://agentmods.dev/badge/skills/tomzx/agents/kill-initiative.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 578 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 $0.00033 $0.00578
Opus 5 $0.00016 $0.00289
Sonnet 5 $0.00007 $0.00116
Haiku 4.5 $0.00003 $0.00058

Measured 6d ago against content hash e68644383a1d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

kill-initiative 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.

skills/pdlc/skills/kill-initiative/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kill Initiative

Killing an initiative is hard and rarely encoded, so it gets its own skill. It converts a kill gate verdict (or a manual decision to stop) into a durable record, frees the capacity the initiative was consuming, and tells stakeholders.

Prerequisites

  • Apply the shared PDLC conventions in skills/pdlc/references/shared.md.
  • The initiative to stop ($1 as INIT-N, or resolve from .pdlc/state.yml).

Steps

  1. Locate the initiative directory under .pdlc/initiatives/.
  2. Record the kill via make-decision (general decision) if no gate decision already recorded it. The decision body states the rationale: the strongest evidence that killed it (negative experiment, no real problem, cost > value, guardrail breach).
  3. Update the initiative's progress.md: set current_phase: killed, record killed_at date, and write a one-line rationale.
  4. Reallocate capacity: update .pdlc/context/roadmap.md to remove or downgrade the initiative from its Now/Next/Later slot, freeing the slot for the next priority.
  5. Capture a learning via run-retrospective so the kill produces organizational knowledge, not just a silent deletion. What did we believe that turned out false?
  6. Notify stakeholders: produce a brief via brief-stakeholders summarizing the decision, the rationale, and the capacity freed. Do not send anything without explicit user confirmation (commit/push/PR gate).
  7. If the initiative had already shipped something, consider whether sunset-product is also needed for the shipped artifact.

Output Format

## Initiative killed: INIT-N — <title>

Rationale: <one paragraph>
Evidence: <what we learned>
Capacity freed: <roadmap slot / person-weeks>
Stakeholder brief: <drafted, pending send>
Learning: <captured in .pdlc/learnings/>

Outcome

If $OUTCOME_YAML is set, emit verdict: killed.

Next Step

Run prioritize to refill the freed roadmap slot, or run-retrospective if not already done.

Completion Checklist

  • A decision record exists recording the kill rationale
  • progress.md marked killed with date and rationale
  • Roadmap capacity reallocated
  • A learning captured so the kill compounds knowledge
  • Stakeholder brief drafted (sending requires explicit confirmation)

Read the full file on GitHub · 53 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. 6d ago First seen · 53 lines · 33 tokens per session scan A e68644383a1d

Subscribe to this mod's changes

kill-initiative is a skill published in the GitHub repository tomzx/agents (6 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 578 once invoked, about $0.0002 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 2026-09-03.

Related

Other skills, from other repositories