colombo: Skill for Claude Code

.agents/skills/colombo-improvement-review/SKILL.md

colombo-improvement-review is a skill for Claude Code, Codex from kkeril/colombo. It costs 40 tokens per session (363 once invoked), scanned A, original, MIT.

A review workflow for examining feedback from Colombo, an internal assistant or system, and suggesting small updates to its instructions and documentation.

In plain words
What is it for?
It is for reviewing feedback, identifying failure patterns, proposing updates to AGENTS.md, system cards, runbooks, or routing and redaction rules, and writing regression prompts.
Why use it?
It helps find repeated mistakes and turn them into proposed rules or tests. Changes require owner approval, so the workflow does not alter production systems by itself.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is kkeril/colombo's own configuration. It tells Claude Code and Codex how to work on colombo 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 colombo configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kkeril/colombo. 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/kkeril/colombo/main/.agents/skills/colombo-improvement-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/kkeril/colombo

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.

agentmods badge for colombo-improvement-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/kkeril/colombo/colombo-improvement-review/github.svg)](https://agentmods.dev/skills/kkeril/colombo/colombo-improvement-review)
Your own site
<a href="https://agentmods.dev/skills/kkeril/colombo/colombo-improvement-review"><img src="https://agentmods.dev/badge/skills/kkeril/colombo/colombo-improvement-review/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 colombo-improvement-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/kkeril/colombo/colombo-improvement-review"><img src="https://agentmods.dev/badge/skills/kkeril/colombo/colombo-improvement-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 363 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 $0.00040 $0.00363
Opus 5 $0.00020 $0.00181
Sonnet 5 $0.00008 $0.00073
Haiku 4.5 $0.00004 $0.00036

Measured 11d ago against content hash d1da9ad5aa58, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

colombo-improvement-review 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 11d 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/colombo-improvement-review/SKILL.md · 48 lines

What it actually says

Colombo improvement review skill

Use this skill for Colombo's self-improvement loop: review stored Slack feedback, find repeat failure patterns, and propose small owner-reviewable setup changes.

Rules

  • Do not mutate production systems or external source repositories.
  • Do not apply improvements without owner approval.
  • Do not add secrets, raw logs, private customer data, or credentials to setup files.
  • Prefer durable rules in AGENTS.md; use workspace/connected-systems/*.md only for longer system-specific cards.
  • Put generated regression prompts in workspace/test-messages/*.md.
  • Every suggested change must cite the feedback or job pattern that caused it.

Review steps

  1. Read recent feedback summaries from the configured state directory.
  2. Group weak answers by Weak-answer patterns: wrong or missing connected system, unsupported conclusion, missing timeline, missing blast radius, missing cross-check, unsafe detail, poor Slack formatting, or unclear next step.
  3. Propose the smallest instruction change that would prevent the pattern from recurring.
  4. Add Slack regression prompts that would catch the issue next time.
  5. Write a Markdown suggestion for workspace/improvements/pending/<date>.md.

Output format

# Colombo improvement suggestion

## Review scope
- Jobs reviewed:
- Weak-answer patterns:

## Suggested changes
### 1. <short name>
- Target file:
- Change summary:
- Why this helps:
- Evidence from feedback/job ids:
- Risk / owner review notes:

## Proposed patch guidance

## Suggested Slack regression tests
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. 11d ago First seen · 48 lines · 40 tokens per session scan A d1da9ad5aa58

Subscribe to this mod's changes

colombo-improvement-review is a skill published in the GitHub repository kkeril/colombo (2 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 363 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 2026-08-31.