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-craft-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-craft-doctrine)<a href="https://agentmods.dev/skills/delorenj/mcp-server-trello/mcp-server-trello-craft-doctrine"><img src="https://agentmods.dev/badge/skills/delorenj/mcp-server-trello/mcp-server-trello-craft-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-craft-doctrine"><img src="https://agentmods.dev/badge/skills/delorenj/mcp-server-trello/mcp-server-trello-craft-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 | $0.00259 | $0.04296 |
| Opus 5.5 | $0.00104 | $0.01718 |
| Sonnet 5.5 | $0.00052 | $0.00859 |
| Haiku 4.5 | $0.00026 | $0.00430 |
Grade A, and why
mcp-server-trello-craft-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 — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcp-server-trello-craft-doctrine
The craft North Star for @delorenj/mcp-server-trello. Its sibling
mcp-server-trello-product-doctrine decides what should exist; this decides
how it is built. They are enforced together — a change clears the product
gates and these — but they are different questions, and conflating them is
how a well-shaped feature ships as a landmine (four ceiling-shaped tools shipped
in 1.7 that TypeError'd on first call — see the standing debts).
Every claim below tagged with a line number was VERIFIED on 2026-07-16 by the research that built
TheGardner, and a release (1.8.0) has landed since, so the whole debt ledger is overdue for a re-verify pass. Re-run the grep before you lean on a line number. Recency is the confidence compass:fdfind --type f --hidden --exclude .git -X ls -lt --time=ctime -r.
The North Star (the whole doctrine in one sentence)
Compile taste into structure, so that using the server well is automatic and using it badly is the harder path.
This is the craft face of the product doctrine's deepest rule — "make it a field, not a verb; surfaced, not queried." There, findings ride along on calls the agent already makes. Here, good engineering rides along on the shape of the code: the tested path is the easy path, the safe path is the only path, the reused engine is closer to hand than the fifth copy-paste. The maintainer's years of architecture judgment stop being tribal knowledge the moment they are the path of least resistance for the next contributor — including his future self at 2am.
Passive habit injection is the goal, not a slogan. A doctrine you must remember to apply is a filter (product doctrine, Card Aging: a tool you must remember to invoke is a filter). A doctrine baked into defaults, choke points, and gates applies itself. Prefer the mechanism that removes the choice over the convention that asks for discipline.
The epistemic contract (shared with the whole doctrine family)
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 · 298 lines · 259 tokens per session scan A c4390ccb98dc
mcp-server-trello-craft-doctrine is a skill published in the GitHub repository delorenj/mcp-server-trello (446 stars, last pushed 7d ago), licensed MIT. It adds 259 tokens to every session and 4,296 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
platform-apex-generate
Primary Apex authoring skill for class generation, refactoring, and review. ALWAYS ACTIVATE when the user mentions Apex, .cls, triggers, or asks to create/refactor a class (service, selector, domain, batch, queueable, schedulable, invocable, DTO, utility, interface, abstract, exception, REST resource). Use this skill…
flow-next-impl-review
Carmack-level implementation review of changes via the configured backend. Use when asked to review code or a diff in a flow-next repo.
flow-next-resolve-pr
Resolve PR review feedback. Fetches unresolved threads, triages, fixes, replies and resolves via GraphQL. Use when asked to address review comments.
api-contract-review
Use when auditing CloudBase cloud API wrappers, MCP tools, generated action metadata, or related docs for outdated or incorrect action names, parameters, casing, request shapes, or missing contract tests, especially during periodic quality review or before preparing corrective PRs.
ring:migrating-to-lib-observability
Migrating a Lerian Go app off lib-commons observability imports (deprecated shims or removed APIs) to lib-observability via a fixed mapping table, then bumps go.mod and validates the build; ring:backend-go applies the edits. Covers log/zap/runtime/assert, opentelemetry/tracing, HTTP middleware, context helpers, and…
ring:mapping-streaming-events
Mapping the eventable points in a Lerian Go service where lib-streaming should emit past-tense, durable, tenant-scoped business events, producing a PM-validated event catalog and instrumentation-map.json for ring:instrumenting-streaming-events. Three-pass discovery (Survey, Slice, Mark) with a scope fence and delivery…