A project-maintenance tool for tracking code cleanup that has been noticed but is not urgent. It keeps these items in a shared TECHDEBT.md file, where tech debt means cleanup postponed for later.

Use it to record lint, formatting, style, and other small code cleanups for later work.

It separates ordinary cleanup from risks, open decisions, and future features. Completed items can be removed instead of kept as historical records.

tech-debt — Skill for Claude Code and Codex by pantheon-org

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add pantheon-org/tekhne --skill tech-debt

Clone the repo

git clone --depth 1 https://github.com/pantheon-org/tekhne

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/pantheon-org/tekhne/tech-debt/github.svg)](https://agentmods.dev/skills/pantheon-org/tekhne/tech-debt)

Your own site

<a href="https://agentmods.dev/skills/pantheon-org/tekhne/tech-debt"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/tech-debt/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/pantheon-org/tekhne/tech-debt"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/tech-debt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 174 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,101 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. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 3 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

high Tool Misuse · line 23
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
medium Excessive Agency · line 130
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
medium Excessive Agency · line 133
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00174	$0.03101
Opus 5	$0.00087	$0.01550
Sonnet 5	$0.00035	$0.00620
Haiku 4.5	$0.00017	$0.00310

Measured 9d ago against content hash d05d05308f00, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

tech-debt 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 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/validate-tech-debt-schema.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/project-mgmt/tech-debt/SKILL.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tech Debt

A single committed table (docs/TECH_DEBT.md) of code-level cleanup that isn't a risk, a shortcut, or an open decision (docs/RISK_REGISTER.md's job) and isn't a future feature (docs/ROADMAP.md's job) -- just things that should get tidied up when there's spare time. Sibling to the risk-register skill, sharing its scaffolding pattern (dedicated skill, YAML row template, JSON schema, validation script) but not its append-only invariant: a tech-debt row is deleted once fixed, not archived, because there is no decision to keep evidence of.

Rules

A row is deleted once fixed, not archived. Unlike risk-register's docs/RISK_REGISTER.md, there is no append-only guard here and no technical backstop preventing deletion -- that is the deliberate design, not a gap. A concurrent-edit merge that drops a still-open row alongside a legitimate deletion is a known, accepted limitation of this model; it is not engineered around, because the whole point of choosing this model over risk-register's is to avoid that machinery for low-stakes items.
Enforcement is local pre-commit only, not CI-backed, not GitHub-server-enforced. scripts/validate-tech-debt-schema.sh, wired into pre-commit via lefthook, blocks a locally-committed malformed row. A commit made through the GitHub web UI or API, git commit --no-verify, or from a machine without lefthook installed is not stopped by this.
Due diligence runs in both directions. Before filing a row, confirm the item is genuinely just cleanup --not a risk, shortcut, or open decision that belongs in docs/RISK_REGISTER.md instead. Before deleting a row (marking it fixed), confirm the fix didn't reveal a real cost or risk; if it did, promote it to docs/RISK_REGISTER.md first (see Workflow) rather than letting the row vanish with the discovery unrecorded.

Prerequisites

docs/TECH_DEBT.md exists. If this is the first entry in a project and the file doesn't exist yet, create it with a # Tech Debt title, an intro paragraph drawing the boundary against RISK_REGISTER.md/ROADMAP.md/aislop's baseline, the enforcement-scope caveat from Rule 2, and an empty table using the columns in assets/templates/tech-debt-row-template.yaml.
assets/templates/tech-debt-row-template.yaml -- the shape of a single row, illustrated
assets/schemas/tech-debt-row.schema.json -- the same shape, as enforceable constraints
scripts/validate-tech-debt-schema.sh, wired into pre-commit (lefthook), so a malformed row can never be committed. No append-only companion (Rule 1).
jq (schema constraints are read at runtime, never hardcoded -- see Scripts) and shellcheck (CI and pre-commit both gate the validator script), both pinned in mise.toml.

Read the full file on GitHub · 182 lines

Files

What ships with it

18 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

9d ago First seen · 182 lines · 174 tokens per session scan A d05d05308f00

Subscribe to this mod's changes

tech-debt is a skill published in the GitHub repository pantheon-org/tekhne (10 stars, last pushed yesterday), licensed MIT. It adds 174 tokens to every session and 3,101 once invoked, about $0.0009 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.

Project management agent-skills skills tessl

syndic

Gère un parc de copropriétés en France avec vue portfolio consolidée. Couvre administration, comptabilité (décret 2005, plan comptable copro, 5 annexes), assemblées générales (convocation, PV, notification), appels de fonds, travaux, fournisseurs, recouvrement d'impayés et transition de syndic. Maîtrise les majorités…

romainsimon/paperasse · 194 tokens

template-instantiation

Creates .NET projects from templates with validated parameters, smart defaults, Central Package Management adaptation, and latest NuGet version resolution. USE FOR: creating new dotnet projects, scaffolding solutions with multiple projects, installing or uninstalling template packages, creating projects that respect…

managedcode/dotnet-skills · 168 tokens

note-improvement

Capture an out-of-scope improvement opportunity so it doesn't get lost. Use when the user asks to "note improvement", "save improvement", "track this for later", "remember this improvement", "note this idea", "log improvement", "backlog this", or "park this idea". Also invoke proactively when noticing something…

tobihagemann/turbo · 107 tokens

turborepo-monorepo

Provides comprehensive Turborepo monorepo management guidance for TypeScript/JavaScript projects. Use when creating Turborepo workspaces, configuring turbo.json tasks, setting up Next.js/NestJS apps, managing test pipelines (Vitest/Jest), configuring CI/CD, implementing remote caching, or optimizing build performance…

giuseppe-trisciuoglio/developer-kit · 76 tokens

handover-admin

Generate comprehensive admin documentation for AEM Edge Delivery Services project handover. Use when handing over admin responsibilities, onboarding a new site administrator, or documenting admin procedures — e.g., "admin guide", "admin documentation", "admin handover".

adobe/skills · 52 tokens

Product Strategy

A comprehensive skill for product strategy — covering frameworks, opportunity sizing, prioritization, roadmap building, OKRs, and stakeholder management. From early-stage discovery to mature product org execution.

cosmicstack-labs/mercury-agent-skills · 39 tokens