Borrowing it
Nothing to install: this file belongs to delorenj/mcp-server-trello. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/delorenj/mcp-server-trello/main/.agents/skills/mcp-server-trello-product-doctrine/SKILL.mdgit clone --depth 1 https://github.com/delorenj/mcp-server-trelloWrote 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/delorenj/mcp-server-trello/mcp-server-trello-product-doctrine)<a href="https://agentmods.dev/skills/delorenj/mcp-server-trello/mcp-server-trello-product-doctrine"><img src="https://agentmods.dev/badge/skills/delorenj/mcp-server-trello/mcp-server-trello-product-doctrine/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/delorenj/mcp-server-trello/mcp-server-trello-product-doctrine"><img src="https://agentmods.dev/badge/skills/delorenj/mcp-server-trello/mcp-server-trello-product-doctrine.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 | $0.00253 | $0.08715 |
| Opus 5.5 | $0.00101 | $0.03486 |
| Sonnet 5.5 | $0.00051 | $0.01743 |
| Haiku 4.5 | $0.00025 | $0.00872 |
Grade A, and why
mcp-server-trello-product-doctrine 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 — 599 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcp-server-trello — Product Doctrine (SSOT)
The product thesis of @delorenj/mcp-server-trello: the durable rules for
what belongs in this server and what does not. This file is the single source
of truth. The TheGardner product agent and the pr-crusher release gate
both reference it and yield to it — when the doctrine here changes, their
behavior changes with it. They hold personas and workflows; this holds the
thesis.
Facts below were VERIFIED on 2026-07-16, with one block re-verified 2026-07-21 (the 1.8.0 ship — see Ground truth). The maintainer pivots hard and fast; his own guidance is "take any and all docs with a grain of salt." This is a doc. Re-run the commands before you lean on them. Recency is the confidence compass:
fdfind --type f --hidden --exclude .git -X ls -lt --time=ctime -r.
Why this doctrine exists (the structural asymmetry)
The maintainer can't fix this by working harder: the inbound PR flow
structurally cannot produce ceiling work. Contributors see the API surface;
they can't see the product thesis. So they send update_list, dueReminder,
watch_card, custom fields — one more endpoint each, forever. Of the registered
tools, roughly five encode any judgment at all. pr-crusher is the gate on
what arrives. This doctrine is the source of what should exist. Nobody else
is going to build the ceiling.
This is not a hype document. Motivation makes the job harder, not easier — motivated people ship the flattering idea. The value is in what gets killed. In the research that produced this doctrine, 81 candidate tools were generated and every single one was ceiling-shaped; the good ones died anyway, on gates that come before the North Star. Bring an idea's corpse, not its brochure.
The epistemic contract (read this before you believe anything below)
The research that produced this doctrine asserted things it never checked, in
the same confident register as things it proved. It claimed /search was a
permanent moat while its own inputs said Atlassian ships search today. It
invented a user persona and let it kill an entire territory. You will do this
too unless you mark your claims.
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 · 599 lines · 253 tokens per session scan A 6b32e0710d74
mcp-server-trello-product-doctrine is a skill published in the GitHub repository delorenj/mcp-server-trello (446 stars, last pushed 7d ago), licensed MIT. It adds 253 tokens to every session and 8,715 once invoked, about $0.0010 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 2026-09-16.
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.
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.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
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,"…