dev-auto-first

dev-auto-first is a skill for Codex from bearded-illirian/trailmark. It costs 119 tokens per session (2,356 once invoked), scanned A, original, MIT.

An automated coordinator for completing coding work one section at a time. It connects steps for understanding the work, checking existing solutions, planning, and executing changes, then validates each step.

In plain words
What is it for?
Use it for hands-off task execution across several work sections, especially when each section follows the same workflow.
Why use it?
It reduces the need for manual approval between routine steps while still stopping and escalating when a genuine blocker needs a response. A block is one defined section of a larger task.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents); $skill-name invocation.

Good fit Use it for hands-off task execution across several work sections, especially when…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bearded-illirian/trailmark/dev-auto-first
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 bearded-illirian/trailmark --skill dev-auto-first
Clone the repo
git clone --depth 1 https://github.com/bearded-illirian/trailmark

Made for: 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 dev-auto-first

README.md
[![agentmods](https://agentmods.dev/badge/skills/bearded-illirian/trailmark/dev-auto-first.svg)](https://agentmods.dev/skills/bearded-illirian/trailmark/dev-auto-first)
Your own site
<a href="https://agentmods.dev/skills/bearded-illirian/trailmark/dev-auto-first"><img src="https://agentmods.dev/badge/skills/bearded-illirian/trailmark/dev-auto-first.svg" alt="Measured on agentmods" height="20"></a>
Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,356 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00119 $0.02356
Opus 5 $0.00060 $0.01178
Sonnet 5 $0.00024 $0.00471
Haiku 4.5 $0.00012 $0.00236

Measured 3d ago against content hash e4f06268709d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

dev-auto-first scanned grade A with 1 finding 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 3d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Real integration via 3 endpoints on `{ops_host}`. The skill lives in the agent, hits the API via `Bash + curl`.
adapters/codex/.agents/skills/dev-auto-first/SKILL.md · 273 lines

How it starts

The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dev-Auto-First Protocol

Autonomous orchestrator of the per-block cycle. Runs instead of manual approval at each step: flow-first → library-first → plan-first → execute.

Key principle: dev-auto-first does not wait for the user's "ok" — it reads the artifact itself, validates it against the rules, and on success continues the chain. On blockers — it escalates to a chat bot and waits for a reply.

How it differs from manual mode:

Manual dev-auto-first
flow-first waits for "ok" User writes "go" Skill validates artifact → auto-approve
library-first waits for "ok" User writes "go" Skill validates table → auto-approve
plan-first asks for mode User picks 1/2/3 Skill answers "1 — Autopilot"
Blocker in a skill User decides Escalation to chat bot

Important: dev-auto-first is a SKILL, not an agent. Works in the same context, manages sub-skills via Skill() calls.

Input

Task context ({slug}, {log_dir}) plus a list of blocks with status open or pending in the tracking database.

Output

Per-block auto-approve log lines to chat, artifacts from each sub-skill (flow-first / library-first / plan-first / report / user-note), and a final summary table with block statuses + escalation counts.

Hands off to

— (terminal). Final task closure is a separate step (ship-first invoked manually or from a future auto-closer).


Step 0 — Check task context

Check: are {slug} and {log_dir} known in the current session?

If yes — continue to Step 0.5.

If no — list latest task folders under {tasks_root}/log/, request user selection, set {slug} and {log_dir}.

Cannot skip. Without {log_dir} sub-skill artifacts cannot be read.


Step 0.5 — Load the block list

sqlite3 {tasks_root}/routing.db \
  "SELECT block_num, title, status FROM task_blocks
   WHERE task_id='{slug}' AND status IN ('open','pending')
   ORDER BY sort_order;"

Save as {pending_blocks}. If empty — output "No blocks with status open/pending" and finish.

Read the full file on GitHub · 273 lines

Files

What ships with it

2 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.

  1. 3d ago Changed e4f06268709d
  2. 7d ago First seen · 273 lines · 119 tokens per session scan A cb7031acbc26

Subscribe to this mod's changes

dev-auto-first is a skill published in the GitHub repository bearded-illirian/trailmark (19 stars, last pushed 5d ago), licensed MIT. It adds 119 tokens to every session and 2,356 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

mission-control

Interact with Mission Control — AI agent orchestration dashboard. Use when registering agents, managing tasks, syncing skills, or querying agent/task status via MC APIs.

builderz-labs/mission-control · 34 tokens

after-sales

Use when managing post-purchase experience, building customer loyalty, or increasing repeat purchases.

aAAaqwq/AGI-Super-Team · 19 tokens

afrexai-compliance-engine

Your AI compliance officer. Guides startups and scale-ups through SOC 2, ISO 27001, GDPR, HIPAA, and PCI DSS — from zero to audit-ready. No consultants needed.

aAAaqwq/AGI-Super-Team · 0 tokens

bankr

AI-powered crypto trading agent and LLM gateway via natural language. Use when the user wants to trade crypto, check portfolio balances, view token prices, transfer crypto, manage NFTs, use leverage, bet on Polymarket, deploy tokens, set up automated trading, sign and submit raw transactions, or access LLM models…

aAAaqwq/AGI-Super-Team · 96 tokens

competitive-offer-architect

Design irresistible offer packages with real salary benchmarks, negotiation playbooks, and competitive counter-strategies. Co-designed with Siku (司库). Includes total compensation calculator, negotiation scripts, and BATNA analysis.

aAAaqwq/AGI-Super-Team · 48 tokens

ai-viral-team-script-writing

A guide for writing short-video scripts and shot lists, including dialogue, camera direction, character actions, mood, music, hooks, and endings. A shot list describes what happens in each camera shot.

aAAaqwq/AGI-Super-Team · 169 tokens