self-goal

self-goal is a skill for Claude Code, Codex from Windy3f3f3f3f/claude-self-goal. It costs 92 tokens per session (527 once invoked), scanned A, original, MIT.

A tool that sets a concrete completion condition for the current Claude Code session. Claude Code is a coding assistant that can work through tasks in a repository.

In plain words
What is it for?
Use it to keep a session working until tests pass, a build succeeds, a file exists, or another checkable condition is met. It can also clear a goal or set one for another background session you own.
Why use it?
It helps prevent the assistant from stopping before an objective result is reached, such as passing tests or producing a required file.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

Good fit Use it to keep a session working until tests pass, a build succeeds, a file exists, or another checkable condition is met. It can also clear a goal or set one for another background session you own.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/windy3f3f3f3f/claude-self-goal/skill
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 Windy3f3f3f3f/claude-self-goal --skill skill
Clone the repo
git clone --depth 1 https://github.com/Windy3f3f3f3f/claude-self-goal

Made for: Claude Code, Codex.

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 self-goal

README.md
[![agentmods](https://agentmods.dev/badge/skills/windy3f3f3f3f/claude-self-goal/skill/github.svg)](https://agentmods.dev/skills/windy3f3f3f3f/claude-self-goal/skill)
Your own site
<a href="https://agentmods.dev/skills/windy3f3f3f3f/claude-self-goal/skill"><img src="https://agentmods.dev/badge/skills/windy3f3f3f3f/claude-self-goal/skill/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 self-goal

Your own site · 80×15
<a href="https://agentmods.dev/skills/windy3f3f3f3f/claude-self-goal/skill"><img src="https://agentmods.dev/badge/skills/windy3f3f3f3f/claude-self-goal/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 527 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00092 $0.00527
Opus 5 $0.00046 $0.00264
Sonnet 5 $0.00018 $0.00105
Haiku 4.5 $0.00009 $0.00053

Measured 10d ago against content hash 006b3412c509, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

self-goal 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 10d 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.

skill/SKILL.md · 37 lines

What it actually says

self-goal

Give the current session its own native /goal by running the claude-self-goal tool from your Bash tool. It figures out the session type (interactive / tmux / daemon background) and picks the right delivery channel automatically.

When to use

Use this when, mid-task, you conclude you should keep going until a specific, checkable condition holds — and you want Claude Code's built-in goal evaluator (not just your own intention) to keep the session from stopping early.

Good conditions are objective: "all tests in ./test pass", "the file dist/app.js exists", "the build is green". Avoid vague ones like "the code is good".

How

# set a goal on this session (always quote the condition):
claude-self-goal "all tests pass and the build is green"

# clear it early if the plan changes:
claude-self-goal --clear

# set a goal on another background session you own:
claude-self-goal --session <id> "the PR's CI is green"

Replace claude-self-goal with the absolute path if it is not on PATH (e.g. /usr/local/bin/claude-self-goal).

Notes

  • Auto-detected channel: tmux → tmux send-keys (no root); plain interactive → TIOCSTI (needs root); daemon /bg session → claude attach over its rv socket. A headless claude -p session can't take an interactive /goal and is refused.
  • Always quote the condition — an unquoted multi-word condition is split into several arguments by the shell.
  • The condition is injected as a single line; control characters are rejected.
  • Once set, the ◎ /goal active chip appears and Claude Code's native goal evaluator should keep the session working until the condition is evaluated as met. It auto-clears on success — do not tell the user to run /goal clear after the goal is achieved.
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. 10d ago First seen · 37 lines · 92 tokens per session scan A 006b3412c509

Subscribe to this mod's changes

self-goal is a skill published in the GitHub repository Windy3f3f3f3f/claude-self-goal (102 stars, last pushed 2mo ago), licensed MIT. It adds 92 tokens to every session and 527 once invoked, about $0.0005 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.