Skip to main content
Glama
JeanFrancoisGagne

crapkit

by JeanFrancoisGagne
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Files that change together

list_coupled_files
Read-onlyIdempotent

Find file pairs that change together in git history, ranked by coupling strength, so you know what an edit may drag along before you start.

Instructions

Lists file pairs that keep landing in the same commits over the churn window, strongest first, at most 50. Use it before editing a file to learn what an edit drags along, and list_duplicate_functions for copied code. It reads a cached ranking, not the scored run, and walks git log again only when HEAD, the churn window or the clone depth moved. An empty list means no pair cleared both thresholds, not a missing run: min_support 5 needs five shared commits, and min_confidence 0.5 means the rarer file moved with its partner half the time.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
repoNopath to the scored repo's root (default: the repo the server was started in); a leading ~ is the home directory
min_supportNominimum shared commits before a pair counts (default 5)
min_confidenceNominimum P(pair changes together), 0 to 1 (default 0.5)

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
pairsNopairs clearing both thresholds, ordered by support x confidence descending, at most 50
schemaNopayload schema version, 1
truncatedNopresent only when the whole answer was longer than one tool result the server sends (7,500 characters): each list, string or object field it cut, at any depth, keeps its start, and full is the CLI command that prints the whole answer
window_monthsNomonths of git history the pairs were counted over, back from the commit date of HEAD (the config's churn_window_months)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.8.1
    • changedInput schema / properties / repo / description
      Previous value: -"path to the scored repo's root (default: the repo the server was started in)"New value: +"path to the scored repo's root (default: the repo the server was started in); a leading ~ is the home directory"
    • addedOutput schema / properties / truncated
      Added value: +{
+  "description": "present only when the whole answer was longer than one tool result the server sends (7,500 characters): each list, string or object field it cut, at any depth, keeps its start, and full is the CLI command that prints the whole answer",
+  "properties": {
+    "fields": {
+      "additionalProperties": {
+        "properties": {
+          "kept": {
+            "description": "how many the answer keeps",
+            "type": "integer"
+          },
+          "of": {
+            "description": "how many the whole answer has",
+            "type": "integer"
+          }
+        },
+        "type": "object"
+      },
+      "description": "each cut field, named by its keys joined with dots (gate.breaches) -> kept and of: elements for a list, entries for an object, characters for a string",
+      "type": "object"
+    },
+    "full": {
+      "description": "the crapkit command that prints the whole answer, spelled for the server's shell",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}
    • changedOutput schema / properties / window_months / description
      Previous value: -"months of git history the pairs were counted over (the config's churn_window_months)"New value: +"months of git history the pairs were counted over, back from the commit date of HEAD (the config's churn_window_months)"
  2. Addedv0.6.0

TDQS

A4.8/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare it read-only, idempotent and non-destructive, but the description adds real behavior beyond them: it reads a cached ranking rather than the scored run, re-walks git log only when HEAD, the churn window or clone depth moved, and defines what an empty list means. This staleness/invalidation contract is exactly the kind of context annotations cannot express.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose, then usage, then caching and threshold caveats; every sentence earns its place. It is dense and the last sentence packs multiple clauses, but nothing is redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return-value details are not needed. The description covers the caching model, the invalidation triggers, the result cap and ordering, and the empty-result interpretation, leaving no material gap for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description goes further by interpreting the parameters: min_support 5 means five shared commits and min_confidence 0.5 means the rarer file moved with its partner half the time. That gives intuitive meaning to both numeric thresholds beyond the schema's terse text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Lists file pairs that keep landing in the same commits'), plus scope (churn window), ordering (strongest first) and cap (at most 50). It explicitly distinguishes itself from list_duplicate_functions, so an agent can separate the two without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit trigger ('use it before editing a file to learn what an edit drags along') and names the alternative tool plus the condition selecting it ('list_duplicate_functions for copied code'). It also pre-explains the empty-result case so the agent doesn't misread it as a missing run.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools