protocol-conformance-test
Skill0 starsChanged 14 days agoMITView on GitHub
Test the wire protocol directly, so a client bug and a server bug are distinguishable. Use when a client reports a failure and the server's own behaviour is unproven
In this repository49 other files it gives its agents.
- argument-construction-from-artifactsSkill
- audit-log-of-tool-callsSkill
- bounded-output-designSkill
- capability-negotiation-checkSkill
- 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-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
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
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 20
Write the exact JSON-RPC lines the client should send
- Distinctive: line 23
Check the jsonrpc field, id echo and error codes
- Distinctive: line 25
Keep the transcript as a fixture so the test is reproducible
- Distinctive: line 29
every response echoes the request id
≈ “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
Protocol Conformance Test
Test the wire protocol directly, so a client bug and a server bug are distinguishable
Use when: a client reports a failure and the server's own behaviour is unproven
Avoid when: the server is a thin library wrapper with no wire protocol of its own
Procedure
- Write the exact JSON-RPC lines the client should send
- Pipe them into the server process with a bounded timeout
- Assert the response shape, not only the presence of a reply
- Check the jsonrpc field, id echo and error codes
- Repeat for a malformed line and for an unknown method
- Keep the transcript as a fixture so the test is reproducible
Signals
- every response echoes the request id
- malformed input produces a parse error, not a crash
- an unknown method produces method-not-found
- the server keeps serving after an error line
Patterns
1. Piped transcript
printf '%s\n' '{"jsonrpc":"2.0",...}' | python -m skillmcp serve2. Shape assertion
jsonrpc == '2.0' and id == sent id3. Survival check
send a bad line, then a good one, expect two repliesPitfalls
- Testing through the client library, which hides the raw response
- Asserting only that some output appeared
- Forgetting that a server which crashes on a bad line fails every later call
Done when
- happy path, malformed line and unknown method each have a fixture
- the server is shown to survive an error line
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.

