coding-agent-optimization SKILL.md skillA

coding-agent-optimization from peterbamuhigire/chwezi-dev-engine is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add peterbamuhigire/chwezi-dev-engine/coding-agent-optimization@git:20260929.65e3315

Pins git:20260929.65e3315 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
peterbamuhigire/chwezi-dev-engine
Path
skills/ai/coding-agent-optimization/SKILL.md
Versions recorded
6
Latest version
git:20260929.65e3315, committed Sep 29, 2026
First version recorded
Aug 2, 2026
Size
16,564 bytes
Repository stars
28
License
MIT

Use when auditing or tuning a development machine's Claude Code or Codex setup for context, model, subagent, permission, or token efficiency, deciding when to compact a long session, or running independent lanes in parallel safely. Analyse local capabilities first; apply only supported reversible changes.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Coding Agent Optimisation

Analyse one development device, then tune its coding-agent configuration to
reduce context waste, unnecessary model spend, unsafe delegation, and repeated
work. Keep the canonical procedure vendor-neutral; use the Codex and Claude
Code adapters only after the local runner and schema have been identified.

## Prerequisites

Load `anti-ai-slop`, `skill-composition-standards`, and
`world-class-engineering` first. Load `skill-engine-audit` (skill safety gate) before accepting or
applying a new optimisation workflow. After inventory, load only the relevant
adapter: [Codex](references/codex.md) or [Claude Code](references/claude-code.md).

## When this skill applies

- Audit a new Windows, macOS, Linux, WSL, or container-based development device.
- Tune Codex or Claude Code for smaller bounded workers and cleaner contexts.
- Port an agent configuration to another PC without copying unsupported keys or
  model identifiers.
- Review a configuration that appears to consume too many tokens or spawn too
  many workers.
- Prepare a safe, reversible patch for global or project-level agent settings.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add peterbamuhigire/chwezi-dev-engine/coding-agent-optimization@sha256:2bb3203744ca1457

The line at the top of this page pins the label git:20260929.65e3315, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_rdsua2dm56isntkj.svg)](https://markdownregistry.com/a/art_rdsua2dm56isntkj)

5 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 6 versions of this file, between Aug 2, 2026 and Sep 29, 2026, about one every 11 days.

versioncommittedcommitsizeaudit
git:20260929.65e3315 latest2026-09-29 65e3315 16,564 BA view · diff
git:20260924.eb7972e2026-09-24 eb7972e 16,450 BA view · diff
git:20260916.2b571632026-09-16 2b57163 15,530 BA view · diff
git:20260907.eeff1242026-09-07 eeff124 14,233 BA view · diff
git:20260907.1b775c12026-09-07 1b775c1 11,706 BA view · diff
git:20260802.91933072026-08-02 9193307 11,495 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (16564 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

peterbamuhigire/chwezi-dev-engine · 28 stars · license MIT · pushed 2026-10-22 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_rdsua2dm56isntkj
GET https://markdownregistry.com/api/v1/resolve?ref=peterbamuhigire/chwezi-dev-engine/coding-agent-optimization
GET https://markdownregistry.com/api/v1/blob/2bb3203744ca145743ebf0f4eb0e5d44952a475aee84f58494943838925f0111

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from peterbamuhigire/chwezi-dev-engine

00-meta-initialization SKILL.md skill
peterbamuhigire/chwezi-dev-engine · 00-meta-initialization/SKILL.md · Use when initialising documentation and a methodology roadmap for a brand-new project by detecting project type…
git:20260911.7afa6ea · audit A · 28 stars
new-project SKILL.md skill
peterbamuhigire/chwezi-dev-engine · 00-meta-initialization/new-project/SKILL.md · Use when the task matches skill: new project scaffold and this skill''s local workflow.
git:20260929.68d1fe1 · audit A · 28 stars
AGENTS.md AGENTS.md file
peterbamuhigire/chwezi-dev-engine · AGENTS.md
git:20260929.68d1fe1 · audit A · 28 stars
CLAUDE.md CLAUDE.md file
peterbamuhigire/chwezi-dev-engine · CLAUDE.md
git:20260924.29cdc2b · audit A · 28 stars
chwezi-dev-engine SKILL.md skill
peterbamuhigire/chwezi-dev-engine · SKILL.md · Top-level router for the Chwezi Core Systems web-development and software-engineering skills engine. Use for AI…
git:20260929.68d1fe1 · audit A · 28 stars
ai-agent-commercial-operations SKILL.md skill
peterbamuhigire/chwezi-dev-engine · skills/ai/ai-agent-commercial-operations/SKILL.md · Use when pricing, billing, refunding, recognizing revenue, or packaging commercial terms for agentic AI services, or…
git:20260924.eb7972e · audit A · 28 stars
ai-agent-compliance-controls SKILL.md skill
peterbamuhigire/chwezi-dev-engine · skills/ai/ai-agent-compliance-controls/SKILL.md · Use when mapping AI agent operations to SOC 2, ISO 27001, HIPAA, audit logs, control testing, attestations, and…
git:20260924.eb7972e · audit A · 28 stars
ai-agent-governance-and-limits SKILL.md skill
peterbamuhigire/chwezi-dev-engine · skills/ai/ai-agent-governance-and-limits/SKILL.md · Use when defining agent budgets, step limits, reversibility, blast-radius controls, kill switches, and governance…
git:20260924.29cdc2b · audit A · 28 stars
ai-agent-multi-agent-coordination SKILL.md skill
peterbamuhigire/chwezi-dev-engine · skills/ai/ai-agent-multi-agent-coordination/SKILL.md · Use when designing systems where multiple agents collaborate on one task — supervisor/worker, debate, plan-execute…
git:20260907.1b775c1 · audit A · 28 stars
ai-agent-observability-evaluation SKILL.md skill
peterbamuhigire/chwezi-dev-engine · skills/ai/ai-agent-observability-evaluation/SKILL.md · Use when measuring, evaluating, replaying, evidencing, or tracking success for AI agent tasks, steps, traces, and…
git:20260911.7afa6ea · audit A · 28 stars
ai-agent-runtime-architecture SKILL.md skill
peterbamuhigire/chwezi-dev-engine · skills/ai/ai-agent-runtime-architecture/SKILL.md · Use when designing multi-tenant agent runtimes, control loops, state machines, retries, idempotency, step caps, durable…
git:20260929.c29972d · audit A · 28 stars
ai-agent-safety-and-red-team SKILL.md skill
peterbamuhigire/chwezi-dev-engine · skills/ai/ai-agent-safety-and-red-team/SKILL.md · Use when red-teaming agent tool and data perimeters for indirect prompt injection, action escalation, tenant…
git:20260924.eb7972e · audit A · 28 stars

Every file in peterbamuhigire/chwezi-dev-engine

Browse by kind, by grade A, or by owner.