agentmods.dev

coding.annotate_with_todoai

coding.annotate_with_todoai is a skill for Claude Code from gpsaggese/helpers. It costs 13 tokens per session (387 once invoked), scanned A, original, Apache-2.0.

A code annotation workflow that reads project rules and adds TODO comments at places where a file breaks them. It uses extra testing rules for Python test files.

In plain words
What is it for?
Use it on Python source or test files to identify convention problems and add a TODO describing each required change.
Why use it?
It marks the exact code locations needing attention without fixing them automatically, making rule violations visible during later development.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths.

not rated 158repo +1 today A scan 13 tokens original Apache-2.0

Good fit Use it on Python source or test files to identify convention problems and add a TODO describing each required change.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gpsaggese/helpers/coding.annotate_with_todoai
View source ↗ gpsaggese/helpers
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 gpsaggese/helpers --skill coding.annotate_with_todoai
Clone the repo
git clone --depth 1 https://github.com/gpsaggese/helpers

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 coding.annotate_with_todoai

README.md
[![agentmods](https://agentmods.dev/badge/skills/gpsaggese/helpers/coding.annotate_with_todoai/github.svg)](https://agentmods.dev/skills/gpsaggese/helpers/coding.annotate_with_todoai)
Your own site
<a href="https://agentmods.dev/skills/gpsaggese/helpers/coding.annotate_with_todoai"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/coding.annotate_with_todoai/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 coding.annotate_with_todoai

Your own site · 80×15
<a href="https://agentmods.dev/skills/gpsaggese/helpers/coding.annotate_with_todoai"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/coding.annotate_with_todoai.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 387 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 $0.00013 $0.00387
Opus 5.5 $0.00005 $0.00155
Sonnet 5.5 $0.00003 $0.00077
Haiku 4.5 $0.00001 $0.00039

Measured yesterday against content hash 2a8d3b4e9d9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

coding.annotate_with_todoai 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 yesterday.

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/coding.annotate_with_todoai/SKILL.md · 42 lines

What it actually says

Goal

  • Annotate the file <FILE> with TODOs for each violated rule and convention

Workflow

Determine the Rules to Apply

  • If <FILE> is a Python file, use <RULES>
    • .claude/skills/coding.rules.md
  • If <FILE> is a Python testing file (e.g., test/test_*.py), use <RULES>
    • .claude/skills/coding.rules.md
    • .claude/skills/testing.rules.md
  • Print the rule files <RULES> used for each file in <FILE>
  • Read the rule files <RULES> carefully

Annotate with TODOs

  • Annotate every point in <FILE> that violates <RULES>, adding a TODO before it, like 
    # TODO(ai_gp): Apply <RULE> before the point with violation
  • E.g., 
    # TODO(ai_gp): Apply "Replace Checking Invariants with `assert_equal` - Do not use multiple `assertIn()` calls to check individual pieces of a string output; instead compare the entire output with `assert_equal()`"
self.assertIn("Failed Tests Summary", actual)
self.assertIn("test_method1", actual)
self.assertIn("test_method2", actual)
self.assertIn("Total failing tests: 2", actual)

Ask User to Continue

  • Ask the user to commit and then ask to continue
  • If the user says to continue, run the skill /coding.todoai_gp on <FILE>

Verification

  • Confirm every violation of <RULES> in <FILE> is caught and annotated with a TODO
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. yesterday First seen · 42 lines · 13 tokens per session scan A 2a8d3b4e9d9f

Subscribe to this mod's changes

coding.annotate_with_todoai is a skill published in the GitHub repository gpsaggese/helpers (158 stars, last pushed today), licensed Apache-2.0. It adds 13 tokens to every session and 387 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-11-06.

Code reviewLanguagesPython
Related

coding.annotate_with_todoai compared with skills from other repositories

coding.annotate_with_todoai next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
coding.annotate_with_todoaigpsaggese/helpersSkill158todayApache-2.0A13Claude Code
mcore-linting-and-formattingNVIDIA/skillsSkill3.9ktodayApache-2.0A44Claude Code
splitting-oversized-modulesPostHog/posthog-fossSkill728todayMITA197Claude Code, Codex
python-review-checklistawslabs/cli-agent-orchestratorSkill1.5ktodayApache-2.0A20Claude Code, Codex
splitting-oversized-modulesPostHog/posthogSkill41ktodaynoneA197Claude Code, Codex
best-practicesFradSer/dotclaudeSkill596yesterdayMITA52Claude Code
plankton-code-qualityloulanyue/awesome-claude-notesSkill2711mo agoMITA34Claude Code