modelcontextprotocol/inspector
Watch
1
0
Fork
You've already forked inspector
 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 2

chore: make the workflow skills model-invocable

Browse source 
`disable-model-invocation: true` does not merely make a skill prefer `/name` —
the model cannot invoke it at all, and its description is absent from the skill
listing. So "create a PR for #2163", which is how that work actually starts,
could never reach `pr-flow`. The original rationale ("procedures with side
effects we'd invoke by name anyway") conflates invoking a skill, which only
loads instructions, with performing the procedure it describes.

Flipped `pr-flow`, `pre-push-gate`, `board-ops` and `test-servers` to
model-invocable. `user-invocable` is an independent axis, so this is purely
additive — every `/name` still works. `issue-create`, `issue-triage` and
`release` stay deliberate.

`board-ops` is in the set because `pr-flow` and `issue-create` delegate their
card steps to it: a pointer from a model-invocable skill to a manual-only one is
a dead end for the model.

Costs weighed: the listing share goes 1,199 → 2,256 of 4,000, and a spurious
load costs ~250 characters where a missed one costs a wrong base branch or an
unsigned commit. The rules stay resident in AGENTS.md either way — this improves
the odds of getting the procedure too, it does not become the guarantee.

Eval cases committed for all four, measured at RUNS=3: pre-push-gate, board-ops
and test-servers 5/5; pr-flow 4/5, with "take it through to a pull request" at
100% and the Copilot-review case borderline. Three initial cases were replaced
rather than tuned green: their answers are resident in AGENTS.md, so the model
answering without the skill is correct behaviour, not a miss — the rule this
file already records about what makes a valid trigger case.

AGENTS.md's maintenance rule now says to default to `false` and explains why,
so the advice this change walks back does not get re-applied.

Signed-off-by: cliffhall <cliff@futurescale.com>
This commit is contained in:
cliffhall 2026-08-30 00:00:14 -04:00
commit 94a71f48bc
9 changed files with 117 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

2
.claude/skills/board-ops/SKILL.md
View file

@ -1,7 +1,7 @@
---
name: board-ops
description: gh recipes for the Inspector project boards — add a card, move its Status, set or re-score its Priority, delete a card, and recover from a deleted single-select option. Covers board #28 (v2) and board #11 (v1), their node/field/option IDs, and the option-deletion hazard.
disable-model-invocation: true
disable-model-invocation: false
---
# Board operations

22
.claude/skills/board-ops/evals/evals.json Normal file
View file

@ -0,0 +1,22 @@
[
{
"prompt": "Move the board card for issue 2189 to In Review.",
"expect": "board-ops"
},
{
"prompt": "How do I set the Priority field on a card in the v2 project board?",
"expect": "board-ops"
},
{
"prompt": "The project board rejected my Status option ID. How do I get the current ones?",
"expect": "board-ops"
},
{
"prompt": "Explain the difference between TCP and UDP.",
"expect": null
},
{
"prompt": "What year was the first Moon landing?",
"expect": null
}
]

4
.claude/skills/pr-flow/SKILL.md
View file

@ -1,7 +1,7 @@
---
name: pr-flow
description: Take an issue through to a merged PR — branch naming, the DCO signoff, screenshots, opening the PR against the right base, requesting a Copilot review, responding to review rounds, and closing out (manual close plus Done).
disable-model-invocation: true
description: Take an issue through to a merged PR in this repo, and what to do at each step. Use when asked to open, create or submit a PR; when a DCO or signoff check fails; when requesting a Copilot review or responding to review comments; when naming a branch; when attaching screenshots to a PR; or when closing out after a merge.
disable-model-invocation: false
---
# PR flow

22
.claude/skills/pr-flow/evals/evals.json Normal file
View file

@ -0,0 +1,22 @@
[
{
"prompt": "I've finished the fix for issue 2071. Take it through to a pull request.",
"expect": "pr-flow"
},
{
"prompt": "How do I get Copilot to review a PR in this repo?",
"expect": "pr-flow"
},
{
"prompt": "The DCO check is red on my branch. How do I fix the commits I already pushed?",
"expect": "pr-flow"
},
{
"prompt": "What does this regex match? /^[a-z]+$/",
"expect": null
},
{
"prompt": "Translate 'good morning' into Spanish.",
"expect": null
}
]

4
.claude/skills/pre-push-gate/SKILL.md
View file

@ -1,7 +1,7 @@
---
name: pre-push-gate
description: Run the mandatory pre-push gate and diagnose a failing stage — npm run format then npm run local:gate, what each stage checks, and the known traps (stale tsc cache, symlinked worktree node_modules, concurrent runs, orphaned smoke ports).
disable-model-invocation: true
description: Diagnose a failing stage of this repo's pre-push gate, and run it correctly. Use when npm run local:gate or npm run validate fails; when lint, coverage, a smoke, or Storybook goes red; when a stage behaves differently inside a git worktree; when the whole run times out; or when deciding what to run before pushing.
disable-model-invocation: false
---
# The pre-push gate

22
.claude/skills/pre-push-gate/evals/evals.json Normal file
View file

@ -0,0 +1,22 @@
[
{
"prompt": "npm run local:gate just failed at the coverage stage. What do I do?",
"expect": "pre-push-gate"
},
{
"prompt": "The Storybook stage of the gate fails in my worktree even though the tests pass. What is wrong?",
"expect": "pre-push-gate"
},
{
"prompt": "Everything in the gate started timing out at once. What causes that?",
"expect": "pre-push-gate"
},
{
"prompt": "What is 17 multiplied by 23?",
"expect": null
},
{
"prompt": "Write a limerick about a cat.",
"expect": null
}
]

2
.claude/skills/test-servers/SKILL.md
View file

@ -1,7 +1,7 @@
---
name: test-servers
description: Run a composable MCP test server by hand — pick the showcase config that reproduces a given feature or bug, build test-servers, and connect with the right protocol era. Covers the stale-build hazard.
disable-model-invocation: true
disable-model-invocation: false
---
# Running a test server

22
.claude/skills/test-servers/evals/evals.json Normal file
View file

@ -0,0 +1,22 @@
[
{
"prompt": "I want to reproduce the OAuth token revocation behaviour by hand. Which test server do I run?",
"expect": "test-servers"
},
{
"prompt": "How do I start one of the composable MCP test servers with a config file?",
"expect": "test-servers"
},
{
"prompt": "I renamed a file under test-servers/src and the fixture is still running the old code. Why?",
"expect": "test-servers"
},
{
"prompt": "Sort this list alphabetically: banana, apple, cherry.",
"expect": null
},
{
"prompt": "What is the boiling point of water in Fahrenheit?",
"expect": null
}
]

35
AGENTS.md
View file

@ -16,16 +16,16 @@ users invoke them by name.
| Skill | Covers | How it loads |
| --- | --- | --- |
| [`local-dev`](.claude/skills/local-dev/SKILL.md) | Install and run each client; the `@inspector/core` alias; and the **reasoning** behind Dependency placement below — what each rule defends against and how to tell you have hit one (the rules themselves stay here) | Model-invoked |
| [`project-structure`](.claude/skills/project-structure/SKILL.md) | Which client owns which surface, what is in `core/`, where a new file belongs | Model-invoked (not user-invocable) |
| [`testing`](.claude/skills/testing/SKILL.md) | Where a test file goes, which command runs it, the tiers, clearing the coverage gate, `renderWithMantine` | Model-invoked |
| [`local-dev`](.claude/skills/local-dev/SKILL.md) | Install and run each client; the `@inspector/core` alias; and the **reasoning** behind Dependency placement below — what each rule defends against and how to tell you have hit one (the rules themselves stay here) | Model-invoked, or `/local-dev` |
| [`project-structure`](.claude/skills/project-structure/SKILL.md) | Which client owns which surface, what is in `core/`, where a new file belongs | Model-invoked only |
| [`testing`](.claude/skills/testing/SKILL.md) | Where a test file goes, which command runs it, the tiers, clearing the coverage gate, `renderWithMantine` | Model-invoked, or `/testing` |
| [`issue-create`](.claude/skills/issue-create/SKILL.md) | The five-step create flow: version label, type label, milestone, board card, Status + Priority | `/issue-create` |
| [`issue-triage`](.claude/skills/issue-triage/SKILL.md) | The two-pass sweep of unboarded issues, the priority rubric and its score comment, the board audit | `/issue-triage` |
| [`board-ops`](.claude/skills/board-ops/SKILL.md) | `gh project` recipes and the field/option IDs for boards #28 and #11; the option-deletion hazard and its recovery | `/board-ops` |
| [`pr-flow`](.claude/skills/pr-flow/SKILL.md) | Branch naming, DCO signoff, screenshots, opening the PR, requesting a Copilot review, responding, closing out | `/pr-flow` |
| [`pre-push-gate`](.claude/skills/pre-push-gate/SKILL.md) | Running `npm run local:gate` and diagnosing a failing stage | `/pre-push-gate` |
| [`board-ops`](.claude/skills/board-ops/SKILL.md) | `gh project` recipes and the field/option IDs for boards #28 and #11; the option-deletion hazard and its recovery | Model-invoked, or `/board-ops` |
| [`pr-flow`](.claude/skills/pr-flow/SKILL.md) | Branch naming, DCO signoff, screenshots, opening the PR, requesting a Copilot review, responding, closing out | Model-invoked, or `/pr-flow` |
| [`pre-push-gate`](.claude/skills/pre-push-gate/SKILL.md) | Running `npm run local:gate` and diagnosing a failing stage | Model-invoked, or `/pre-push-gate` |
| [`release`](.claude/skills/release/SKILL.md) | Cutting a release: bump on `v2/main`, milestone merge, tag `origin/main`, publish | `/release` |
| [`test-servers`](.claude/skills/test-servers/SKILL.md) | Picking and running a showcase test server; the stale-build hazard | `/test-servers` |
| [`test-servers`](.claude/skills/test-servers/SKILL.md) | Picking and running a showcase test server; the stale-build hazard | Model-invoked, or `/test-servers` |
Longer-form human documentation lives in [`docs/`](./docs) — see the table in the
[README](./README.md#documentation).
@ -164,10 +164,21 @@ that from happening:
line** — no BOM, no leading blank line.
2. **Every skill declares its invocation mode explicitly.**
`disable-model-invocation` is **required** on every skill (`true` = reachable
only by name, `false` = the model may fire it). Prefer `true` for any procedure
with side effects: it removes the trigger question entirely *and* keeps the
description out of the listing budget. A skill that is background knowledge
rather than an action also sets `user-invocable: false`.
only by name, `false` = the model may fire it). A skill that is background
knowledge rather than an action also sets `user-invocable: false`.
**Default to `false`.** `true` was the original default here, on the argument
that a procedure with side effects would be typed as `/name` anyway — but
*invoking* a skill has no side effects, it loads instructions, and the premise
is false for anything a user asks for in prose. "Create a PR for #2163" is how
that work actually starts, and under `true` the model **cannot** reach the
skill at all: it is absent from the listing and the Skill tool refuses it. The
costs are asymmetric — a spurious load costs ~250 characters, a missed one
costs a wrong base branch or an unsigned commit — and the budget is not tight
(all ten skills would total ~2.8k of 4k). Reserve `true` for a procedure that
is genuinely only ever started deliberately, as `/release` is.
⚠️ **A `true` skill cannot be reached by another skill either.** If a
model-invocable skill says "see `/board-ops`", that pointer is a dead end for
the model unless `board-ops` is model-invocable too.
⚠️ **`paths` is not a free win.** It looks like the deterministic option, and
it does gate loading to matching files — but measured against the `testing`
skill's own eval cases, adding it roughly **halved** the rate at which the same
@ -201,7 +212,7 @@ that from happening:
overflows, and drops the least-invoked entries **first** — which are exactly the
model-invoked skills that must fire on their own. `verify:skills` prints the
current cost against the budget recorded in `scripts/lib/skill-manifest.mjs`
(1,199/4,000 characters as of this writing) and fails when it is exceeded. Raise
(2,256/4,000 characters as of this writing) and fails when it is exceeded. Raise
the budget deliberately, or tighten a description; each entry is capped at 1,536
characters regardless, so **put the key use case first**.