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 skills/gerstep/positioning-plugin/positioningnpx skills add Gerstep/positioning-plugin --skill positioninggit clone --depth 1 https://github.com/Gerstep/positioning-pluginWhat 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 | $0.00116 | $0.01052 |
| Opus 5 | $0.00058 | $0.00526 |
| Sonnet 5 | $0.00023 | $0.00210 |
| Haiku 4.5 | $0.00012 | $0.00105 |
Grade A, and why
positioning 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Positioning
A 15-minute forced-choice session that produces a positioning statement and the artifacts a startup needs to hold a position: message architecture, mind virus, compass, ignore list, worldview, archetype, and a 90-day proof plan.
Position or be positioned. If you don't pick a category, you will be assigned one. The market's default setting is disbelief, so competition has shifted from making claims to surviving verification. This skill forces the choices, then makes every claim either provable today or a dated bet.
Operating rules (read first)
Questions. If an interactive question tool is available (for example AskUserQuestion in Claude Code or Cowork), use it for every forced choice. Otherwise ask in plain text: one question at a time, numbered options, wait for the answer. Never stack questions in plain-text mode.
Forced choice. No "all of the above". Gut answers over polished answers — tell the user 30 seconds per question is enough. The pain of choosing is the exercise.
Time. The session targets 15 minutes total. Never block on research; never loop. Phase budgets are in the session script. If research has not returned by the statement phase, proceed without it and mark the pack "research pending".
Research. If a subagent tool is available, launch research in the background during setup. If only web search is available, run a few quick searches inline between phases. If there is no web access, skip research and say so in the output. Never invent competitors.
Files. All artifacts live in positioning/ under the current working
directory (create it if needed). Never overwrite another founder's answers
file.
Which moment is this?
If the user asked for a specific mode in plain words ("compile", "start
over", "new session"), obey that. Otherwise check positioning/ in the
current directory and route:
| State | Moment | Script |
|---|---|---|
No positioning/ dir, or no answers-*.md files |
First run — run the session | references/session.md |
One or more answers-*.md, no positioning.md |
Ask: run your own session, or compile the team's answers now? | references/session.md or references/compile.md |
positioning.md exists |
Offer: a new founder session, or recompile to update the pack | references/session.md or references/compile.md |
What ships with it
8 files 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.
- 2d ago First seen · 87 lines · 116 tokens per session scan A ed3e8921a438
positioning is a skill published in the GitHub repository Gerstep/positioning-plugin (108 stars, last pushed 26d ago), licensed MIT. It adds 116 tokens to every session and 1,052 once invoked, about $0.0006 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…