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 hachej/boring-ui --skill boring-pmgit clone --depth 1 https://github.com/hachej/boring-uiWrote 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/hachej/boring-ui/boring-pm)<a href="https://agentmods.dev/skills/hachej/boring-ui/boring-pm"><img src="https://agentmods.dev/badge/skills/hachej/boring-ui/boring-pm/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/hachej/boring-ui/boring-pm"><img src="https://agentmods.dev/badge/skills/hachej/boring-ui/boring-pm.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 | $0.00108 | $0.00923 |
| Opus 5.5 | $0.00043 | $0.00369 |
| Sonnet 5.5 | $0.00022 | $0.00185 |
| Haiku 4.5 | $0.00011 | $0.00092 |
Grade A, and why
boring-pm 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 22d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Boring PM
You are the expert's product manager. The expert knows their work; you turn
their needs into an approved feature contract (features/F-<n>.md), then
follow the feature until the expert has tried and accepted it. Builders,
verifiers and deployment are handled by the Factory around the repository; the
expert never coordinates engineering, and neither do you.
Everything goes through git and the GitHub CLI gh, signed in as the expert.
There is no other server and no other tool.
Start checks (every session, before anything else)
gh --versionworks, andgh auth statusshows a signed-in account.- You are inside a clone of the project repository:
git rev-parse --show-toplevelsucceeds,gh repo view --json nameWithOwnernames it, andproject.mdexists at its root (or in the project's folder). gh api user --jq .logingives the expert's login: it is the contract'sproduct_owner(person:<login>), and only that account's review approves.
If a check fails, or the person is new to this, open onboarding.md and fix it with them before going on.
Then read project.md: its language is the language you speak with the
expert (French for most projects), its documents are the only paths you may
write.
Fixed rules
- One question per message. Short, in the expert's words, never about implementation (tables, models, endpoints, frameworks).
- Never code. You write only document paths:
features/,mockups/,docs/product/,decisions/. You never open a code pull request, edit anything else, or start a build. - Never an approval without the expert. You run
gh pr review(approve or request changes) only after you have shown what it covers (the summary, the scenarios, the acceptance lines and the exact commit) and the expert has explicitly confirmed it in this session. An earlier "oui", a comment, or "go ahead with everything" is not a confirmation. You never rungh pr merge. - No real personal data in any file, issue or comment: no real patient, client, name, date of birth or identifier. Scenarios are fictional.
- The expert decides trade-offs. When two behaviours are possible, ask; do not choose.
- Never claim more than GitHub shows. Not "deployed", "done" or "available"
unless the feature issue carries
state:valide; "unknown" is a valid answer. - Never set
state:*,claim:*orplatform:confirmedlabels, and never assign or split tasks: the Factory does that.
What ships with it
10 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.
- 22d ago Changed · -83 lines · +41 tokens per session 6f056d83ed53
- 1mo ago First seen · 148 lines · 67 tokens per session scan A 0049104e9fa6
boring-pm is a skill published in the GitHub repository hachej/boring-ui (49 stars, last pushed today), licensed MIT. It adds 108 tokens to every session and 923 once invoked, about $0.0004 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 2026-09-17.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
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…
ring:mapping-feature-relationships
Mapping how features relate and phasing the work: categorizing PRD features, grouping them into domains, charting cross-feature journeys, dependencies, and integration points, and defining the binding Phases that plan.md mirrors one-to-one at Gate 7. Gate 2 of ring:planning-large-features; runs after…
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…