Keep privilege visible beside usage counts
The tool’s power should be obvious without reading deep into its schema.
QI
Capabilities Detail
A capability detail page should explain one tool or skill as an execution affordance: what it does, who uses it, and how it changes reach or risk.
Use This Page When Asking
What does this capability actually enable, and how much does that change consequence for the attached work?
Open c6 raw detailSessions
24
Broad session reuse
Invocations
340
High-demand tool lane
Error rate
0%
Healthy on the current baseline
Reach
shell + files
High-power surface
Why This Detail Matters
Important Metadata
Name
read_file
Type
tool
Source
Claude Code
Category
filesystem
Agent
claude-code@1.2.0
Capability ID
tool:builtin:read_file
What This Detail Should Help Decide
Use representative sessions as proof, not as the page definition
The detail should stay capability-centered even when the supporting evidence is session-based.
Let the reviewer move from tool power to session context in one click
The page should make it easy to confirm whether the high-power surface was used as expected.
Capability-Centered Topology
A capability map should connect a tool or skill to its source, callers, sessions, and failure patterns.
Useful per capability: whether it is a tool or skill, who invokes it, where it comes from, which sessions depend on it, and whether volume or errors suggest attention.
Capability
read_file
Representative high-frequency tool; the same topology applies to skills by swapping source path for MCP or builtin origin.
22 sessions · 318 invocations
Type
tool
Category
filesystem
Source
builtin
Error posture
0.3%
Callers
Who reaches for this capability.
Claude Codeprimary agent
Cursorsecondary agent
alice@company.comfrequent user
Source Surface
Where the capability originates.
builtintool source
filesystemcategory
write_fileadjacent tool
Session Context
Where it shows up inside work.
coding sessionsdominant workflow
/src/auth.tscommon target
session detailtrace invocations
Watch For
The operational and governance questions.
web_search 3.4%peer outlier
parameter misuseschema check
skill path driftfor skill variants
Representative Event Chain
The page should show how the item participates in a readable sequence, not just a pile of supporting rows.
- 1
Definition
The page establishes what the capability actually does
The schema and description should tell the reviewer why this tool changes reach more than a simple name does.
bashtoolshell - 2
Demand
Session reuse shows whether the tool is a core lane or an edge utility
Invocation volume should stay near session count so the reviewer sees recurring demand, not just isolated use.
24 sessions340 invocations - 3
Risk fit
Privilege and error context change how the tool should be interpreted
Direct shell or file reach can be high-consequence even when the current error rate is low.
shell reach0% errors - 4
Verification
The reviewer pivots into sessions after understanding the capability surface
Once the tool is framed, recent-session rows help confirm whether it appeared in ordinary or sensitive work.
recent sessionssession detail
c6 Evidence Tables
Input Schema
c6 exposes the capability contract directly on the detail page.
| Field | Type | Required |
|---|---|---|
| path | string | yes |
| offset | number | no |
| limit | number | no |
Recent Sessions Using This Capability
The raw page ties the tool back to recent execution lanes.
| User | Agent | Invocations | Status |
|---|---|---|---|
| alice@company.com | Claude Code | 18 | active |
| carol@company.com | Claude Code | 9 | active |
| dave@company.com | Claude Code | 5 | ended |
Return To Category
Compare this representative detail against the full category framing and drill targets.
Open Capabilities overviewOpen c6 Raw Detail
Use the original detail page for exact raw evidence after the c12 story framing.
Open c6 raw detailOpen c6 Raw List
Compare this item against the broader c6 entity ledger once the representative story is clear.
Open c6 raw list