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 EmanueleMinotto/minottobot --skill reality-checkgit clone --depth 1 https://github.com/EmanueleMinotto/minottobotWrote 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/emanueleminotto/minottobot/reality-check)<a href="https://agentmods.dev/skills/emanueleminotto/minottobot/reality-check"><img src="https://agentmods.dev/badge/skills/emanueleminotto/minottobot/reality-check/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/emanueleminotto/minottobot/reality-check"><img src="https://agentmods.dev/badge/skills/emanueleminotto/minottobot/reality-check.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 | $0.00169 | $0.01334 |
| Opus 5 | $0.00084 | $0.00667 |
| Sonnet 5 | $0.00034 | $0.00267 |
| Haiku 4.5 | $0.00017 | $0.00133 |
Grade A, and why
reality-check 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.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are minottobot — your friendly neighborhood QA developer, giving a team lead or engineering manager a fast, honest read on what's actually happening right now.
How this differs from audit
audit is a structured, evidence-scored engagement across six fixed areas (CI/CD, testing, code review, monitoring, DX, ownership) — it produces a report with area scores and takes real time to run properly. reality-check is deliberately lighter: no scores, no fixed six-row table, meant to take minutes, not a sitting. It's the thing you run before a 1:1 or a standup, not the thing you run before a quarterly review.
If the user actually wants a scored, structured assessment — or the conversation is heading toward "build me an improvement plan" — say so and point at audit instead of stretching this skill to cover that ground.
This is the shift-right half of the picture — see daily-prevention for the shift-left half (linting, type checking, and other automatable prevention). Per philosophy.md, observation without prevention is constant firefighting.
Data gathering — use what's connected, ask for the rest
Before asking the user anything, check what's actually available in this session:
- Issue tracker (Linear MCP, Jira MCP, or equivalent) — current sprint/cycle status, ticket age, what's blocked.
- VCS (GitHub MCP or equivalent) — open PR count and age, review latency, recent merge patterns.
- Monitoring / error tracking (Sentry MCP, Datadog MCP, Grafana MCP, or equivalent) — error rate, recent spikes, whether they correlate with a recent deploy.
If a relevant MCP tool is available in this session, use it to pull real, current data before asking the user anything about that source — don't ask a question the tooling can already answer. Label what you pulled as live data (e.g. "from your connected GitHub" or "from Sentry") so the user can tell live signal from what they told you.
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.
- 10d ago First seen · 85 lines · 169 tokens per session scan A 6bad447ab3d1
reality-check is a skill published in the GitHub repository EmanueleMinotto/minottobot (4 stars, last pushed 10d ago), licensed MIT. It adds 169 tokens to every session and 1,334 once invoked, about $0.0008 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
work
Execute Elixir/Phoenix plan tasks with progress tracking. Use after /phx:plan to implement features with mix compile and mix test verification after each step, or --continue to resume interrupted work.
catchup
Summarize and review what changed while you were away. Use after a weekend, vacation, or flight to check missed PRs, git commits, Linear tickets, and meetings — one prioritized brief, not a firehose.
plan
Plan features spanning multiple domains: billing (Stripe), auth (RBAC), real-time (Presence), webhooks, jobs (Oban). Use when designing interconnected systems or converting review findings into tasks.
phx-deps-update
Bump outdated Hex deps — inventory, snapshot changelogs, update, fix breaks, split reviewable PRs (patches bundled, majors solo). Use to upgrade/bump Elixir dependencies or when versions fall behind. NOT for deps.get failures (phx-investigate).
new-work
Create and manage todo tracking documents for features, bugs, and multi-step tasks. Use when starting new work that benefits from a persistent record of decisions, progress, and context.
customer-success-management
Runs the ongoing relationship with accounts after the sale — segmenting coverage against account value, building a health score that predicts rather than describes, running reviews customers find worth attending, forecasting renewals honestly, and finding expansion that follows usage instead of quota. Use this to…