agent-crm: Skill for Claude Code

.agents/skills/debug-crm-run/SKILL.md

debug-crm-run is a skill for Claude Code from khaoss85/agent-crm. It costs 90 tokens per session (508 once invoked), scanned A, original, MIT.

A guided workflow for diagnosing failed or unexpected Accordo CRM operations. It uses health checks, run traces, audit events and module state to investigate what happened.

In plain words
What is it for?
Use it after an Accordo workflow or CRM operation fails or produces an unexpected result. It helps inspect the project, check its health, examine execution traces, and identify the cause.
Why use it?
It separates missing or incompatible capabilities from failures during an actual run. This reduces guesswork when a workflow, API operation, provider call or approval transition behaves incorrectly.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: installed under .agents/ (shared by several agents).

This is khaoss85/agent-crm's own configuration. It tells Claude Code how to work on agent-crm itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent-crm configures →

Part of the accordo plugin — 12 skills, 2 MCP servers shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to khaoss85/agent-crm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/khaoss85/agent-crm/main/.agents/skills/debug-crm-run/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/khaoss85/agent-crm

Made for: Claude Code.

Or install accordo, the plugin that ships this one along with the rest of its 12 skills, 2 MCP servers.

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 debug-crm-run

README.md
[![agentmods](https://agentmods.dev/badge/skills/khaoss85/agent-crm/debug-crm-run.svg)](https://agentmods.dev/skills/khaoss85/agent-crm/debug-crm-run)
Your own site
<a href="https://agentmods.dev/skills/khaoss85/agent-crm/debug-crm-run"><img src="https://agentmods.dev/badge/skills/khaoss85/agent-crm/debug-crm-run.svg" alt="Measured on agentmods" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 508 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 $0.00090 $0.00508
Opus 5 $0.00045 $0.00254
Sonnet 5 $0.00018 $0.00102
Haiku 4.5 $0.00009 $0.00051

Measured 7d ago against content hash 8afeca406f87, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

debug-crm-run 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.

.agents/skills/debug-crm-run/SKILL.md · 32 lines

What it actually says

Orient yourself first

npm run crm -- app inspect --json

Read valid, then problems[], then limitations[], in that order. Every problem is fixed or reported before anything is built on top of it, and every limitation is a hard boundary on what you may claim. Then read packages[], capabilities[], resources[], actions[], policies[] and providers[]: that list is what exists. A capability absent from the report does not exist, whatever a record name, a label or a document suggests.

If the repository documents this skill names are absent, you are in a project built from this framework rather than in the framework itself. The inspection report is then the source of truth and those documents are optional background — do not guess at their contents, and do not assume a path exists because this skill names it.

A composition problem explains a whole class of failed runs, so rule it out before reading a single trace. Note also that the report is source-only: it never opens the database, so it can tell you an action exists and never why one run of it failed.

  1. Run npm run doctor.
  2. Read the workflow run with the MCP crm_get_trace tool or GET /api/traces/:id.
  3. Identify the first failed or semantically incorrect step; do not treat downstream symptoms as the root cause.
  4. Compare audit events with the expected module state.
  5. Reproduce in an isolated test before editing production logic.
  6. Fix the smallest responsible service, workflow step or provider adapter.
  7. Add a regression test and run npm run verify.
  8. Record a decision only when the fix changes architecture or policy.
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 · 32 lines · 90 tokens per session scan A 8afeca406f87

Subscribe to this mod's changes

debug-crm-run is a skill published in the GitHub repository khaoss85/agent-crm (2 stars, last pushed 5d ago), licensed MIT. It adds 90 tokens to every session and 508 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories

error-handling-contracts

Design consistent backend and API error handling contracts. Use when Codex is asked to define error response shapes, status codes, validation errors, retry behavior, logging, observability, client-safe messages, or failure semantics.

jeremylongworth-source/AgentSkills · 49 tokens

deepstream-sop

Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the…

NVIDIA/skills · 219 tokens

earth2studio-create-datasource

Create and validate Earth2Studio data source wrappers (DataSource, ForecastSource, DataFrameSource, ForecastFrameSource) from remote stores. Do NOT use for fetching data with existing sources, model inference, or installation tasks.

NVIDIA/skills · 53 tokens

convex-performance-audit

Audits Convex performance for reads, subscriptions, write contention, and function limits. Use for slow features, insights findings, OCC conflicts, or read amplification.

openclaw/clawhub · 38 tokens

ssl-proxy-troubleshoot

Systematic workflow for troubleshooting SSL/proxy connectivity issues with government websites.

HKUDS/OpenSpace · 20 tokens

doca-socket-relay

Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…

NVIDIA/skills · 236 tokens