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.
npx agentmods add instructions/aboudjem/goalify/agents-mdgit clone --depth 1 https://github.com/Aboudjem/goalifyWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01886 | $0.01886 |
| Opus 5 | $0.00943 | $0.00943 |
| Sonnet 5 | $0.00377 | $0.00377 |
| Haiku 4.5 | $0.00189 | $0.00189 |
Grade A, and why
goalify AGENTS.md 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — goalify
Instructions for AI agents and coding assistants working in or invoking this repository. Plain
Markdown, no required fields (per the AGENTS.md convention: the agent parses the text below).
Human-facing docs live in README.md; this file holds the extra context an agent needs.
What this repo is
This repo is goalify, a Claude Code / Agent Skills skill that turns a big coding task into a
self-contained implementation brief plus the /goal completion condition derived from it. In one session it researches the task, locks the few real decisions
(asking the user only the genuine forks, one interactive MCQ batch), and authors two artifacts: a
self-contained implementation brief at an absolute path, and the condition string derived from
that brief's definition of done. The user then runs /clear and pastes the condition into /goal, so a
fresh session executes the big task at full context, proves every criterion in a closeout turn, and
archives the brief on success.
The repo is the skill at skills/goalify/SKILL.md, the /goalify author. There is no script to run;
the skill's output is the brief plus the condition. /goal takes a condition string, never a file
path — the docs say "Run /goal followed by the condition you want satisfied" and the shipped
binary contains No goal set. Usage: /goal <condition> with no file-path branch. The evaluator behind
/goal has no tools and cannot read files, so a path handed to it can never be verified
(Claude Code 2.1.139+, https://code.claude.com/docs/en/goal).
How an agent should invoke / honor the skill
- If running inside Claude Code with the skill installed: trigger it by describing the user's intent,
e.g. "goalify this: ", "prep a goal", "make the brief for /goal", "set up an autonomous run to
launch later". Claude Code matches these to the skill's
descriptionand loadsSKILL.md. - Install: the plugin (
claude plugin marketplace add Aboudjem/10xthenclaude plugin install goalify@10x), or drop in manually:git clone https://github.com/Aboudjem/goalify, then copyskills/goalifyinto~/.claude/skills/. The runner is Claude Code's built-in/goal; goalify does not ship its own. - This skill AUTHORS a handoff file; it does not execute the task. If the user wants the work done
immediately in the current session, that is
autopilot/ultrawork/ralph, not goalify.
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.
- 2d ago First seen · 112 lines · 1,886 tokens per session scan A eabc5b520818
goalify AGENTS.md is an instructions file published in the GitHub repository Aboudjem/goalify (1 stars, last pushed 22d ago), licensed MIT. It adds 1,886 tokens to every session, about $0.0094 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 2026-08-31.
Other instructions, from other repositories
zeroshot CLAUDE.md
Claude Code instructions for the-open-engine/zeroshot, covering zeroshot: multi-agent coordination engine, 🔴 critical rules, 🔴 general purpose requirement (critical), 🔴 behavioral standards and where to look.
zeroshot AGENTS.md
AGENTS.md instructions for the-open-engine/zeroshot, covering zeroshot: multi-agent coordination engine, critical rules, where to look, cluster worker contracts and cli quick reference.
gobby CLAUDE.md
Claude Code instructions for GobbyAI/gobby, covering claude.md, guiding principles, progressive tool discovery enforced by hooks, do not run the full pytest suite and plan mode.
omux CLAUDE.md
Claude Code instructions for Happenmass/omux, covering claude.md, what is omux, commands, code style and architecture.
gobby AGENTS.md
AGENTS.md instructions for GobbyAI/gobby, covering gobby — project context, guiding principles, progressive tool discovery enforced by hooks, do not run the full pytest suite and plan mode.
gobby GEMINI.md
Gemini CLI instructions for GobbyAI/gobby, covering gobby — project context, guiding principles, progressive tool discovery enforced by hooks, do not run the full pytest suite and plan mode.