kc-em-triage

kc-em-triage is a skill for Claude Code from iamcxa/kc-claude-plugins. It costs 44 tokens per session (6,084 once invoked), scanned A, original, MIT.

A workflow for examining Linear issues and turning them into practical implementation guidance. Linear is a tool teams use to track work and customer requests.

In plain words
What is it for?
Use it to assess technical feasibility, decompose issues, explore the codebase, and record guidance for teammates.
Why use it?
It helps split oversized or unclear work and connect requested changes to the code and technical constraints.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Cursor.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the kc-team-ops plugin — 8 skills, 3 agents shipped together

Good fit Use it to assess technical feasibility, decompose issues, explore the codebase, and record guidance for teammates.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add iamcxa/kc-claude-plugins
Claude Code
/plugin install kc-team-ops

Made for: Claude Code.

Or install kc-team-ops, the plugin that ships this one along with the rest of its 8 skills, 3 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for kc-em-triage

README.md
[![agentmods](https://agentmods.dev/badge/skills/iamcxa/kc-claude-plugins/kc-em-triage/github.svg)](https://agentmods.dev/skills/iamcxa/kc-claude-plugins/kc-em-triage)
Your own site
<a href="https://agentmods.dev/skills/iamcxa/kc-claude-plugins/kc-em-triage"><img src="https://agentmods.dev/badge/skills/iamcxa/kc-claude-plugins/kc-em-triage/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for kc-em-triage

Your own site · 80×15
<a href="https://agentmods.dev/skills/iamcxa/kc-claude-plugins/kc-em-triage"><img src="https://agentmods.dev/badge/skills/iamcxa/kc-claude-plugins/kc-em-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,084 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00044 $0.06084
Opus 5 $0.00022 $0.03042
Sonnet 5 $0.00009 $0.01217
Haiku 4.5 $0.00004 $0.00608

Measured 7d ago against content hash 3a4a79fce18e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

kc-em-triage scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

kc-team-ops/skills/kc-em-triage/SKILL.md · 512 lines

How it starts

The opening of the file, as written. The whole thing — 512 lines — stays where its author put it; the contents beside it link to each section on GitHub.

EM Triage

Read Linear issues, explore the codebase, discuss with user, then post structured implementation guidance as Linear comments for human colleagues to execute.

REQUIRED: Use linear-expert skill for Linear operations (loaded by linear-manager agent).

Linear Customer Requests

Customer Need tracking in Linear — MCP tools (list_customers, save_customer, save_customer_need) and usage in triage/overview. See ${CLAUDE_PLUGIN_ROOT}/reference/meeting-notes-flow.md for full concept and API details.

Project Creation (Step P)

When customer needs cluster around a theme with no existing project, propose creating one. Always GATE before creating — draft table with name/lead/target for user confirmation. See ${CLAUDE_PLUGIN_ROOT}/reference/project-creation-flow.md for structured description format and full process.

Process Flow

digraph em_triage {
  rankdir=TB;
  node [shape=box];

  start [label="User invokes /kc-em-triage"];

  node [shape=diamond];
  input [label="Input type?"];

  node [shape=box];
  issues [label="Identify issues\n(IDs, filter, or list)"];
  doc [label="Read document → brainstorm\n→ code-explore per block\n→ linear-manager split\n→ GATE → create issues\n(see decompose-flow.md)"];
  meeting [label="Read meeting source\n→ extract customer + needs\n→ GATE → save to Linear\n(see Step M)"];

  em_lens_entry [label="Step 1.5: EM Lens entry\n(em-lens-scanner)\n→ depth decision\n(🟢/🟡/🔴)"];

  node [shape=diamond];
  depth [label="Depth?"];
  mode [label="Mode?"];

  node [shape=box];
  overview [label="Overview: batch-read\n→ EM Lens table\n(includes Alignment, Depth)"];
  read [label="Read single issue\n+ comments + Customer Needs"];
  explore [label="Multi-layer explore\n(code + docs + knowledge)\n→ skill discovery\n🔴: + memory/journal/git/Sentry"];

  node [shape=diamond];
  deliberate [label="Deliberation gate"];

  node [shape=box];
  debate [label="decision-debate\n(2+ approaches)"];
  brainstorm [label="brainstorming\n(scope unclear)"];
  research [label="em-researcher\n(tech uncertainty)"];
  decompose [label="Decompose\n(scope too large)\nsee decompose-flow.md"];
  design_spec [label="Design spec\n(brainstorm → spec doc\n→ GATE)"];

  em_lens_exit [label="Step 4.5: EM Lens exit\n(assignment candidates\n+ skill/pattern awareness\n+ cost of inaction 🔴)"];
  discuss [label="Discuss → draft comment\n→ GATE → post to Linear"];

  start -> input;
  input -> issues [label="issues"];
  input -> doc [label="document"];
  input -> meeting [label="meeting-notes"];
  doc -> overview [label="issues created"];
  meeting -> issues [label="needs saved\n→ link/create issues"];

  issues -> em_lens_entry;
  em_lens_entry -> depth;

  depth -> discuss [label="🟢 Quick\n(skip explore)"];
  depth -> mode [label="🟡 Standard\n🔴 Deep"];

  mode -> overview [label="overview"];
  mode -> read [label="deep-dive"];
  overview -> read [label="user picks"];

  read -> explore -> deliberate;
  deliberate -> em_lens_exit [label="path clear"];
  deliberate -> debate -> em_lens_exit;
  deliberate -> brainstorm -> em_lens_exit;
  deliberate -> research -> em_lens_exit;
  deliberate -> decompose -> overview;
  deliberate -> design_spec -> em_lens_exit;

  learning [label="Step 7: Learning\n(D1 general → learned-patterns.md\nD2 project → CLAUDE.md)"];

  em_lens_exit -> discuss;
  discuss -> read [label="next issue"];
  discuss -> learning [label="all issues done"];
}

Read the full file on GitHub · 512 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 512 lines · 44 tokens per session scan A 3a4a79fce18e

Subscribe to this mod's changes

kc-em-triage is a skill published in the GitHub repository iamcxa/kc-claude-plugins (3 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 6,084 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories