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 Goldziher/basemind --skill mcp-tool-checklistgit clone --depth 1 https://github.com/Goldziher/basemindWrote 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/goldziher/basemind/mcp-tool-checklist)<a href="https://agentmods.dev/skills/goldziher/basemind/mcp-tool-checklist"><img src="https://agentmods.dev/badge/skills/goldziher/basemind/mcp-tool-checklist/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/goldziher/basemind/mcp-tool-checklist"><img src="https://agentmods.dev/badge/skills/goldziher/basemind/mcp-tool-checklist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 70 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00017 | $0.01484 |
| Opus 5 | $0.00009 | $0.00742 |
| Sonnet 5 | $0.00003 | $0.00297 |
| Haiku 4.5 | $0.00002 | $0.00148 |
Grade A, and why
mcp-tool-checklist 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Tool Checklist
Use this when extending basemind's MCP surface. Skipping a step leaves the tool half-wired.
The surface is nine domain tools, not one tool per verb. Adding a capability means adding a
mode to an existing domain — code, graph, git, memory, web, agents, workspace,
shell, admin. Adding a tenth top-level tool is a surface change that needs its own ADR, not a
checklist step: every extra name competes for the same keyword search in hosts that defer tools, and
GH #50 showed one bad schema takes the whole registry down with it.
Each domain owns a types_<domain>.rs / tools_<domain>.rs / helpers_<domain>.rs trio. Every
file stays under the 1000-line cap enforced by tests/max_lines.rs — split into
helpers_<domain>_<area>.rs rather than raising it.
Steps
-
src/mcp/mode.rs— add the variant to that domain'sdefine_mode!block: the Rust name, the wire spelling, and a short meaning. The macro generates the enum,ALL_MODES,parse(),telemetry_key(), and a flat{"type":"string","enum":[…]}schema. Never#[derive(JsonSchema)]on a doc-commented enum — that emitsoneOf, the construct that silently dropped the entire registry in GH #50. Drop the domain prefix the old flat name carried (search_symbols→codemodesymbols); keep it only where the bare word would be ambiguous. -
src/mcp/types_<domain>.rs— add any new parameter as an optional sibling on the domain's flat<Domain>Paramsstruct (Option<T>+#[serde(default)]). Never a nested struct or a schema union:tests/mcp_schema_wire.rsforbids$ref/$defs/oneOf/anyOf/allOf, and schemars emits$reffor nested types. Paths areRelPath, neverString. Limits default to 100 and cap at 1000. -
src/mcp/helpers_<domain>.rs— add the dispatch arm inrun_<domain>, and add the mode's accepted fields to the per-mode allow-list. The allow-list is inverted deliberately: with a dozen modes and dozens of sibling fields, an explicit per-mode reject list is where a newly added field silently becomes accept-everywhere. Userequire_fieldfor anything the mode cannot run without, so the error names the exactmode/field pair. A field belonging to another mode must be rejected, not ignored — an ignored parameter reads to an agent as a successful call that honoured it. Applyscan_cap = limit * 8when iterating an index range.
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 First seen · 92 lines · 17 tokens per session scan A 2aa1a3c9ba74
mcp-tool-checklist is a skill published in the GitHub repository Goldziher/basemind (99 stars, last pushed 7d ago), licensed MIT. It adds 17 tokens to every session and 1,484 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
projectatlas
Use ProjectAtlas as the atlas-first orientation layer before broad source reads, with MCP-first task startup, short-alias worktree registration and routing, safe targeted initialization, ranked navigation, exact or federated graph evidence, purpose curation, health, lint, and repository-wide token reporting.
codex-coding-plugin
Build, review, or fix ProjectAtlas plugin/runtime installer integration for Codex, Claude Code, and OpenCode, especially version convergence, stale ProjectAtlas cache repair, MCP config generation, skill artifacts, host smoke tests, and fake-host tests for ProjectAtlas releases.
haiku-rag
Search, read and compute over the user's haiku.rag knowledge base through the haiku-rag MCP tools. Use whenever a request could be answered from the user's ingested documents, when asked to find, look up, check or cite something in their documents or knowledge base, or when the question is about the user's own…
trace-mcp-refactoring
Safe refactoring workflow using trace-mcp — assess risk, find candidates, check impact, and rename symbols across all files without missing import sites or cross-file references.
lsp-refactor
End-to-end safe refactor workflow — blast-radius analysis, speculative preview, apply to disk, verify build, run affected tests. Inlines lsp-impact + lsp-safe-edit + lsp-verify + lsp-test-correlation into one coordinated sequence.
lsp-explore
Tell me about this symbol": hover + implementations + call hierarchy + references in one pass — for navigating unfamiliar code.