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 Knuckles-Team/mattermost-mcp --skill mattermost-mcp-developmentgit clone --depth 1 https://github.com/Knuckles-Team/mattermost-mcpWrote 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/knuckles-team/mattermost-mcp/mattermost-mcp-development)<a href="https://agentmods.dev/skills/knuckles-team/mattermost-mcp/mattermost-mcp-development"><img src="https://agentmods.dev/badge/skills/knuckles-team/mattermost-mcp/mattermost-mcp-development/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/knuckles-team/mattermost-mcp/mattermost-mcp-development"><img src="https://agentmods.dev/badge/skills/knuckles-team/mattermost-mcp/mattermost-mcp-development.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 | $0.00043 | $0.00691 |
| Opus 5.5 | $0.00017 | $0.00276 |
| Sonnet 5.5 | $0.00009 | $0.00138 |
| Haiku 4.5 | $0.00004 | $0.00069 |
Grade A, and why
mattermost-mcp-development 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 9d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mattermost-mcp development
This repository owns the Mattermost transport, mappings, MCP tools, and
agent entry points. Shared connector contracts and transports belong to
scion-sdk; admission, serving, and durable graph state belong to
their owning repositories. Read AGENTS.md before changing code and keep
provider credentials and endpoints out of source, logs, and skill content.
Rapid delivery: the 5-minute contract
Specs are already designed. Deliver small, reviewable slices and cite the owning spec row in the commit trailer.
- Find the owning row first with
git grep -n "<term>" -- specsand extend that spec before adding new requirement text. - Reuse existing SDK clients, transport policies, and tool factories. Do not create a second implementation of a connector capability.
- Keep changes scoped to this connector. A change owned by the SDK, Arbora, or the knowledge graph belongs in that repository instead.
- Every delivered requirement needs a bound test. Generated
status.jsonfiles are produced bypipelines-hook spec-status; never hand-edit them. - One logical change per commit, with
Spec: <ID>and the assisting agent trailer adjacent in the final paragraph.
Setup and gates
Use the pinned environment from uv sync --locked. Run the repository
gate from the checkout root:
uvx pre-commit run --all-files
For focused feedback, run the relevant tests with the repository's pinned environment, for example:
uv run --all-extras pytest tests/test_mcp_server.py -q
uv run --all-extras pytest tests/test_api_client.py -q
The canonical .pre-commit-config.yaml delegates connector-standard,
secrets, spec, and tests-fast checks to Knuckles-Team/pipelines at
rev: main. Do not replace those shared hooks with local copies or bypass
a failing check.
Connector-specific checks
- Keep the MCP and agent surfaces aligned with
scion-sdk. - Validate environment and TLS settings before making provider calls.
- Mock external Mattermost calls in tests; never use live credentials in a local gate.
- Keep
mattermost_mcp/skills/package data intact when adding skills. - Documentation lives under
docs/and is published by the shared Pages workflow; source status records live underspecs/.
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.
- 9d ago Changed 5d5e6d272a22
- 11d ago First seen · 80 lines · 43 tokens per session scan A add531933147
mattermost-mcp-development is a skill published in the GitHub repository Knuckles-Team/mattermost-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 43 tokens to every session and 691 once invoked, about $0.0002 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 2026-10-28.
mattermost-mcp-development compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mattermost-mcp-developmentKnuckles-Team/mattermost-mcp | Skill | 0 | 2d ago | MIT | A | 43 | Claude Code, Codex |
| gitlab-api-developmentKnuckles-Team/gitlab-api | Skill | 10 | yesterday | MIT | A | 49 | Claude Code, Codex |
| media-downloader-developmentKnuckles-Team/media-downloader | Skill | 5 | 3d ago | MIT | A | 41 | Claude Code, Codex |
| freshrss-agent-developmentKnuckles-Team/freshrss-agent | Skill | 0 | 2d ago | MIT | A | 52 | Claude Code, Codex |
| hdhomerun-mcp-developmentKnuckles-Team/hdhomerun-mcp | Skill | 0 | 3d ago | MIT | A | 44 | Claude Code, Codex |
| epistemic-graph-developmentKnuckles-Team/epistemic-graph | Skill | 11 | 15d ago | MIT | A | 117 | Claude Code, Codex |
| systems-manager-developmentKnuckles-Team/systems-manager | Skill | 3 | 3d ago | MIT | A | 65 | Claude Code, Codex |