capability-negotiation-check
Skill0 starsChanged 14 days agoMITView on GitHub
Declare only the capabilities the server implements and refuse calls outside them. Use when the server exposes tools and the client must know whether to look for resources or prompts
In this repository49 other files it gives its agents.
- argument-construction-from-artifactsSkill
- audit-log-of-tool-callsSkill
- bounded-output-designSkill
- changelog-and-versioningSkill
- concurrency-and-ordering-checkSkill
- context-window-managementSkill
- credential-isolationSkill
- data-retention-policySkill
- description-as-contractSkill
- destructive-action-confirmationSkill
- destructive-tool-gatingSkill
- deterministic-command-choicesSkill
- done-when-criteriaSkill
- error-shape-for-agentsSkill
- fixture-driven-transcript-testsSkill
- human-in-the-loop-escalationSkill
- idempotency-annotationSkill
- input-schema-strictnessSkill
- least-privilege-tool-grantsSkill
- lifecycle-test-initialize-then-toolsSkill
- local-vs-remote-boundarySkill
- one-procedure-per-skillSkill
- pagination-and-limit-disciplineSkill
- parallel-tool-call-safetySkill
- protocol-conformance-testSkill
- protocol-version-handshakeSkill
- publishing-a-pack-locallySkill
- rate-limit-respectSkill
- reference-canonicalisationSkill
- replay-transcript-for-regressionSkill
- restart-and-reload-semanticsSkill
- scope-guard-before-executionSkill
- search-then-fetch-patternSkill
- secrets-via-environmentSkill
- server-discovery-and-trustSkill
- signal-and-pitfall-sectionsSkill
- skill-frontmatter-contractSkill
- stdio-client-configSkill
- stdout-purity-checkSkill
- third-party-server-sandboxingSkill
- tool-call-budgetingSkill
- tool-call-error-pathsSkill
- tool-error-without-retry-stormSkill
- tools-list-schema-validationSkill
- tool-surface-minimisationSkill
- tool-verb-namingSkill
- transport-choiceSkill
- verify-tool-output-before-reportingSkill
- when-to-use-and-avoidSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 23
Verify the client only calls what was advertised
- Distinctive: line 24
Add a test that asserts undeclared capabilities are refused
- Distinctive: line 25
Update the declaration the same commit a new capability ships
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Capability Negotiation Check
Declare only the capabilities the server implements and refuse calls outside them
Use when: the server exposes tools and the client must know whether to look for resources or prompts
Avoid when: the server is a thin wrapper over one tool and capability breadth is irrelevant
Procedure
- List what the server can do: tools, resources, prompts, sampling
- Declare exactly that subset in the initialize response
- Return method-not-found for capabilities that were not declared
- Verify the client only calls what was advertised
- Add a test that asserts undeclared capabilities are refused
- Update the declaration the same commit a new capability ships
Signals
- the response capabilities block matches the implemented handlers
- an undeclared method returns a JSON-RPC method-not-found error
- the client hides features the server did not advertise
- a new handler without a capability entry is caught by the test
Patterns
1. Tools only
"capabilities": {"tools": {"listChanged": false}}2. Refusal shape
method_not_found for resources/list when undeclared3. Parity test
declared capabilities == implemented handlersPitfalls
- Declaring resources because a future version might add them
- Leaving an undeclared handler reachable, which clients will not exercise and tests will not cover
- Forgetting listChanged semantics when the tool list is dynamic
Done when
- declared capabilities match implemented handlers exactly
- undeclared methods return a clean JSON-RPC error
References
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

