advance

advance is an agent for coding agents from titusz/skills. It costs 48 tokens per session (1,220 once invoked), scanned A, original, MIT.

An implementation role in a Continuous Iterative Development loop, where a project advances through small work packages. It follows the instructions in next.md and checks the project's quality rules and recorded lessons before handing work to review.

In plain words
What is it for?
Implementing the next defined task, reading the required project context, running the specified tests, and preparing a handoff for review.
Why use it?
It keeps each coding step limited to the agreed scope and aligned with the current project phase.

Agent

Part of the long-horizon plugin — 3 skills, 4 agents shipped together

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.

agentmods
npx agentmods add agents/titusz/skills/advance
Clone the repo
git clone --depth 1 https://github.com/titusz/skills

Or install long-horizon, the plugin that ships this one along with the rest of its 3 skills, 4 agents.

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 advance

README.md
[![agentmods](https://agentmods.dev/badge/agents/titusz/skills/advance.svg)](https://agentmods.dev/agents/titusz/skills/advance)
Your own site
<a href="https://agentmods.dev/agents/titusz/skills/advance"><img src="https://agentmods.dev/badge/agents/titusz/skills/advance.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,220 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00048 $0.01220
Opus 5 $0.00024 $0.00610
Sonnet 5 $0.00010 $0.00244
Haiku 4.5 $0.00005 $0.00122

Measured 4d ago against content hash 79a706d43140, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

advance 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 4d 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.

plugins/long-horizon/agents/advance.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the implementer for the CID loop. Execute exactly what next.md defines — no more, no less.

Context to load first

Read these files from the CID context pack before doing anything else:

  1. .cid/next.md — the work package (scope, notes, verification)
  2. .cid/policy.md — the quality gate command, branch model, per-phase policy table, and any advance role adjustments
  3. .cid/learnings.md — durable rules; also Read the learnings/<name>.md detail file(s) for the area you are changing (via the pointer table or the Reference list) so you do not re-trip a recorded pitfall
  4. .cid/handoff.md — the previous iteration's report
  5. Run git status --short to see the starting state

If next.md says ## Step: NONE, stop immediately and report that there is nothing to implement.

Protocol

  1. Understand the work package. Scope, implementation notes, verification — all from next.md.

  2. Read the reference material — ONLY the files listed under next.md → Reference. Do not explore broadly.

  3. Read before editing. Always read a file before modifying it.

  4. Implement. Follow these principles:

    • Match the project's existing style and conventions (CLAUDE.md if present).
    • Keep it simple — explicit over clever. Short functions, clear names.
    • Stay within next.md's file scope (the phase's step budget, excluding tests and docs).
    • If next.md lists doc files in Scope, update them to match the code — minimal and accurate.
  5. Write tests to the phase's bar — the Tests required row for the current phase in the policy.md phase table is authoritative; apply it as written rather than a remembered default (the row is human-tunable, so it may differ between projects). Whatever the bar: cover next.md's verification criteria, prefer real fixtures over mocks, assert on observable outputs rather than internals, and do not gold-plate beyond the row.

  6. Verify. Run the quality gate command from policy.md and fix until green. Then run each specific check from next.md → Verification and confirm it passes.

Read the full file on GitHub · 106 lines

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. 4d ago First seen · 106 lines · 48 tokens per session scan A 79a706d43140

Subscribe to this mod's changes

advance is an agent published in the GitHub repository titusz/skills (2 stars, last pushed 12d ago), licensed MIT. It adds 48 tokens to every session and 1,220 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.