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 TimboGP/timbogp-marketplace --skill measure-fitgit clone --depth 1 https://github.com/TimboGP/timbogp-marketplaceWrote 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/timbogp/timbogp-marketplace/measure-fit)<a href="https://agentmods.dev/skills/timbogp/timbogp-marketplace/measure-fit"><img src="https://agentmods.dev/badge/skills/timbogp/timbogp-marketplace/measure-fit/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.
<a href="https://agentmods.dev/skills/timbogp/timbogp-marketplace/measure-fit"><img src="https://agentmods.dev/badge/skills/timbogp/timbogp-marketplace/measure-fit.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00145 | $0.01020 |
| Opus 5.5 | $0.00058 | $0.00408 |
| Sonnet 5.5 | $0.00029 | $0.00204 |
| Haiku 4.5 | $0.00015 | $0.00102 |
Grade A, and why
measure-fit 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 1mo 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Measure product/market fit
Define a metric for "have I built something people want?", then steer toward it. You work as the Analyst guide role (../../reference/roles.md) — evidence-minded and honest, especially about the difference between progress and vanity. Read references/product-market-fit.md before judging fit.
When to use
The user needs to set up measurement, interpret their funnel/cohorts, or get an honest read on product/market fit. This is the verify quantitatively stage and the validate-the-lifecycle work that precedes it. For a single assumption test, use run-experiment; for the qualitative MVP interviews, customer-interview (mvp).
Core stance
- Retention is the macro that matters. Revenue is the first form of validation; retention is the ultimate one. People can pay for something they don't use (forgot to cancel, someone else pays); they don't keep using something they don't want. Judge "people want it" primarily on retention.
- Cohorts over funnel snapshots. A single funnel hides what changed; weekly cohorts (group users by join week) show whether last week's change actually moved the needle and handle traffic fluctuations correctly.
- Validate the lifecycle micro before scaling macro. Get ~80% of hand-qualified early adopters through the full cycle (acquisition → activation → retention → revenue → referral) before chasing volume. Scaling before early traction is waste.
- Vanity vs. value metrics. Total signups and page views go up while the business goes nowhere. Track activation and retention.
Procedure
- Load context. Read
.lean/PROGRESS.md(stage),.lean/canvas.md(Key Metrics block), and any prior.lean/metrics/files. - Define the value metrics & key metric. Map the customer lifecycle to AARRR (Acquisition, Activation, Retention, Revenue, Referral; see
references/product-market-fit.md). Pick the single key metric for the current question — usually retention as the macro, with activation as the supporting micro. - Set up measurement. Specify the conversion funnel and weekly cohort report (functionally — what events, grouped how — independent of the analytics tool). For early stage, this can be a manual sheet.
- Validate the lifecycle (micro). Walk the funnel for hand-qualified early adopters; find the leakiest bucket, fix it, reach out to users who dropped. Target ~80% through the full cycle.
- Judge fit honestly. Apply the benchmarks: the Sean Ellis test ("how would you feel if you could no longer use this?" — ≥40% "very disappointed" signals early traction) and the 40% retention month-over-month proxy. State whether the evidence supports fit, with the numbers — don't flatter.
- Pick the engine of growth (when approaching fit). Sticky (retention) / viral (referral) / paid (margins; LTV > 3×CAC). Focus on one; declare the key metric and target, and align the next experiments to it (route to
run-experiment). - Write
.lean/metrics/<YYYY-MM-DD>-<label>.md: the funnel/cohort read, the fit verdict against benchmarks, and the recommended next move. Update.lean/PROGRESS.md; if fit signal is real, advance the Stage to Scale.
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.
- 1mo ago First seen · 42 lines · 145 tokens per session scan A 84e1846141da
measure-fit is a skill published in the GitHub repository TimboGP/timbogp-marketplace (3 stars, last pushed 13d ago), licensed MIT. It adds 145 tokens to every session and 1,020 once invoked, about $0.0006 per session on Opus 5.5. 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
gan-zhong-xue
A learning workflow that makes an AI explain code changes through questions, evidence, and underlying principles. It is designed to help developers understand work they asked an AI to do, rather than merely accept the result.
explain
Explain what a piece of code does — a specific file, class, or method in close detail, or a user-facing flow as a concise system overview. What it does and why, not whether it's good.
qector-educator
Teaching and documentation content for quantum error correction with QECTOR: beginner-to-advanced tutorials, ELI5 explanations of syndromes / decoders / parity checks, Tanner-graph visual explanations, and local Markdown teaching material. Load for explanations, course material, or documentation generation.
kb-friendica
Background knowledge about Friendica, the federated social networking platform (Facebook alternative). Covers Friendica's history and lineage (Mistpark 2010, Friendika, Friendica, the Red Matrix/Hubzilla fork), its multi-protocol architecture (ActivityPub, DFRN, Diaspora protocol simultaneously), the DFRN protocol…
learn-from-fix
Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.
elixir-idioms
OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.