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 skills add rordi-ai/loopbreaker --skill shape-strategygit clone --depth 1 https://github.com/rordi-ai/loopbreakerWrote 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.
[](https://agentmods.dev/skills/rordi-ai/loopbreaker/shape-strategy)<a href="https://agentmods.dev/skills/rordi-ai/loopbreaker/shape-strategy"><img src="https://agentmods.dev/badge/skills/rordi-ai/loopbreaker/shape-strategy.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00065 | $0.00723 |
| Opus 5 | $0.00032 | $0.00362 |
| Sonnet 5 | $0.00013 | $0.00145 |
| Haiku 4.5 | $0.00006 | $0.00072 |
Grade A, and why
shape-strategy 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 8d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shape Strategy
Frame the bet before decomposing implementation. Produce a small decision packet, not a feature spec and not a backlog.
Workflow
- Inspect existing repository and product context before asking factual questions.
- State the proposed problem/opportunity in one sentence: who changes behavior, what changes, and why now.
- Separate appetite from estimate:
- Appetite is how much time the outcome is worth.
- Estimate is how long the current shape may take.
- Cut scope to appetite; do not inflate appetite to fit a solution.
- Identify hidden one-way doors: migrations, public APIs, destructive data changes, security boundaries, pricing, or external commitments. Name each material risk with a mitigation; an empty risk list must be an explicit conclusion, not an omitted section.
- Propose the smallest slice that tests the bet and explicitly name non-goals.
- Define a measurable success signal that is stronger than “it shipped.”
- Recommend exactly one disposition:
proceed,spike,park, orreject. - When an issue contract exists, persist the packet with
shape_record. This authoring action does not approve planning; a separate$review-planningagent owns that decision.
The premise is not yours to author
$discovery-interview runs above this skill and produces a founder-approved
discovery record. Your job is to project that approved premise into shape
fields, not to invent one. Every shape field should trace to a recorded answer;
read it with loopbreaker discovery ISSUE.
Shape cannot reach proceed without that record, so an issue arriving here
without one is not a shaping problem — it is a missing interview.
Ask only for product judgment that cannot be learned from available context or
from the approved record. Batch at most four independent questions. Lead with a
recommendation and concrete trade-offs. Do not conduct an exhaustive interview
for a broad initiative; confirm the framing and reserve detailed decisions for
the first executable slice — the exhaustive walk belongs one stage up, at issue
grain, in $discovery-interview.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 82 lines · 65 tokens per session scan A 05934e18c9fe
shape-strategy is a skill published in the GitHub repository rordi-ai/loopbreaker (3 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 723 once invoked, about $0.0003 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 skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.