TechDebtMCP: Skill for Claude Code

.claude/skills/refresh-self-scan/SKILL.md

refresh-self-scan is a skill for Claude Code from PierreJanineh/TechDebtMCP. It costs 52 tokens per session (869 once invoked), scanned A, original, MIT.

A repository self-scan workflow that runs a technical-debt analysis and synchronises its results across the project's main documentation files.

In plain words
What is it for?
Use it after relevant code, configuration, analyzer, rule, or plugin-release changes to refresh the scan and update TECHDEBTSCAN.md, README.md, ARCHITECTURE.md, and CONTRIBUTING.md together.
Why use it?
It prevents health scores, debt scores, issue counts, and remediation estimates from disagreeing between the canonical scan report and related documentation.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions CLAUDE.md.

This is PierreJanineh/TechDebtMCP's own configuration. It tells Claude Code how to work on TechDebtMCP 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 TechDebtMCP configures →

Reuse

Borrowing it

Nothing to install: this file belongs to PierreJanineh/TechDebtMCP. 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/PierreJanineh/TechDebtMCP/develop/.claude/skills/refresh-self-scan/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/PierreJanineh/TechDebtMCP

Made for: Claude Code.

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 refresh-self-scan

README.md
[![agentmods](https://agentmods.dev/badge/skills/pierrejanineh/techdebtmcp/refresh-self-scan.svg)](https://agentmods.dev/skills/pierrejanineh/techdebtmcp/refresh-self-scan)
Your own site
<a href="https://agentmods.dev/skills/pierrejanineh/techdebtmcp/refresh-self-scan"><img src="https://agentmods.dev/badge/skills/pierrejanineh/techdebtmcp/refresh-self-scan.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 869 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 $0.00052 $0.00869
Opus 5 $0.00026 $0.00434
Sonnet 5 $0.00010 $0.00174
Haiku 4.5 $0.00005 $0.00087

Measured 7d ago against content hash 91c50a6b3fe9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

refresh-self-scan 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.

.claude/skills/refresh-self-scan/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Refresh Self-Scan

CLAUDE.md declares TECH_DEBT_SCAN.md as the canonical source of truth for the four self-scan metrics. Three derivative documents (README.md Self-Scan Results, ARCHITECTURE.md Current Status, CONTRIBUTING.md Configuration Impact) must agree with it and must be updated in the same commit. This skill performs that synchronization end-to-end.

When to run

After any of:

  • A code change that could plausibly move the metrics (new analyzer, new rule, custom-rules engine change).
  • A .techdebtrc.json change.
  • An MCPB / plugin release where the README is publicly visible.

Do not run as part of routine bug fixes or docs-only PRs — the rule in .claude/rules/docs-maintenance.md only requires a refresh when the numbers actually move.

Procedure

1. Run the scan

Use the locally installed dogfood MCP (tech-debt-mcp-local), not the published package — the published version may lag behind src/.

mcp__tech-debt-mcp-local__analyze_project { path: "<repo-root>" }
mcp__tech-debt-mcp-local__get_sqale_metrics { path: "<repo-root>" }

Capture: Health Score, Debt Score, Total Issues, Remediation Time (and SQALE rating if it changed).

2. Compare against TECH_DEBT_SCAN.md

Read TECH_DEBT_SCAN.md. If any of the four metrics moved by more than the noise threshold (≥0.1 health/debt point, ≥1 issue, ≥5 min remediation), continue. Otherwise stop and report "no change."

3. Update TECH_DEBT_SCAN.md first

TECH_DEBT_SCAN.md is the canonical source — edit it before any derivative file so a partial commit can never produce divergence. Update:

  • The four metric values
  • "Last Updated" timestamp (ISO date)
  • Any top-issue or category-breakdown sections that depend on the scan

4. Propagate to the three derivative files

In the same commit, update:

File Block to touch
README.md "Self-Scan Results" block
ARCHITECTURE.md "Current Status" block
CONTRIBUTING.md "Configuration Impact" block

Read the full file on GitHub · 75 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 · 75 lines · 52 tokens per session scan A 91c50a6b3fe9

Subscribe to this mod's changes

refresh-self-scan is a skill published in the GitHub repository PierreJanineh/TechDebtMCP (7 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 869 once invoked, about $0.0003 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

prompt-optimization

Improves LLM-facing context while preserving intent, execution boundaries, and proportional work. Use when creating or reviewing prompts, agent definitions, skill definitions, or other instructions for an LLM.

shinpr/rashomon · 42 tokens

recipe-eval-prompt

Compares original and optimized prompts through repeated blind paired execution in git worktrees. Use when evaluating prompt improvement effects or learning prompt engineering through concrete examples.

shinpr/rashomon · 36 tokens

knowledge-base

Retrieves and updates project-specific prompt knowledge from comparison evidence and user feedback. Use only for prompt analysis or post-comparison learning within a Rashomon evaluation.

shinpr/rashomon · 34 tokens

worktree-execution

Creates, pins, and cleans isolated Git worktree pairs for comparison trials. Use only when a Rashomon prompt or skill evaluation needs paired execution environments or orphan recovery.

shinpr/rashomon · 38 tokens

interview-me

Deep-dive spec interviewer. Reads a file, GitHub issue, or requirement, analyzes it against the codebase, then conducts a rigorous 1-on-1 interview using AskUserQuestion to produce a comprehensive, opinionated specification document. Acts as a collaborative architect with active pushback. Also runs --verify to detect…

Sorbh/interview-me · 79 tokens

codecartographer

Drive the CodeCartographer MCP server to reverse-engineer a repository or synthesize a new project through validated analysis phases. Use when asked to run CodeCartographer, analyze or reverse-engineer a codebase, produce architecture/contracts/protocols/defect/porting/reimplementation artifacts, or operate a…

HuginnIndustries/CodeCartographer · 72 tokens