agentsb-roadmap

A maintenance agent for the SwiftASB repository that reviews command-line schema changes, public API boundaries, documentation, checks, and routine upkeep.

In plain words
What is it for?
It is for inspecting repository facts, proposing or applying low-risk maintenance changes when approved, and writing reports for uncertain or risky changes.
Why use it?
It separates safe, evidence-backed maintenance from changes that need human review, reducing the risk of silently changing behavior or public promises.

Agent

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/gaelic-ghost/swiftasb/agentsb-roadmap
Clone the repo
git clone --depth 1 https://github.com/gaelic-ghost/SwiftASB
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,840 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 $0.00000 $0.01840
Opus 5 $0.00000 $0.00920
Sonnet 5 $0.00000 $0.00368
Haiku 4.5 $0.00000 $0.00184

Measured 3d ago against content hash 24c8d460bfb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentsb-roadmap 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 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.

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.

docs/agents/agentsb-roadmap.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentSB Roadmap

AgentSB is the repo-local maintenance agent app for SwiftASB. Its job is to help maintainers keep Codex CLI schema review, SwiftASB public API boundaries, docs, probes, and routine repo upkeep moving without turning uncertain upstream changes into silent source edits.

Operating Model

AgentSB classifies each maintenance opportunity into one of three outcomes.

Outcome Meaning Default action
auto-apply The candidate change is proven non-behavioral, does not affect public API, and is covered by deterministic checks. Apply only when the maintainer opts into safe auto-apply.
draft-only The candidate change is useful but needs review because it changes meaning, docs promises, validation expectations, or non-public implementation details. Write a proposed patch and report, but do not apply it automatically.
report-only The candidate needs human classification or is too risky to draft confidently. Write a durable report with evidence and decisions needed.

AgentSB should default to report-only whenever safety is uncertain.

Planned Workflow

  1. Inspect deterministic repo facts. AgentSB reads the current branch, dirty state, reviewed Codex CLI window, schema dump directories, promoted wire files, maintainer docs, and package metadata without calling the OpenAI API.

  2. Produce a durable report. AgentSB writes tracked reports under docs/agents/reports/ so maintenance history survives local cleanup tools and can be reviewed like normal docs.

  3. Run evals. Local evals verify deterministic behavior without credentials. AI-assisted evals verify coordinator and specialist behavior when OPENAI_API_KEY is available.

  4. Compare schema families. AgentSB compares schema dumps across Codex CLI versions, identifies added, removed, and changed families, and records the evidence in generated reports.

  5. Prototype private local Codex storage inspection when explicitly requested. AgentSB may use read-only direct ingest for maintainer reports and SwiftASB design evidence when the storage version is recognized and private text stays redacted by default. The destination capability belongs in SwiftASB.

Read the full file on GitHub · 199 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. 3d ago First seen · 199 lines · 0 tokens per session scan A 24c8d460bfb2

Subscribe to this mod's changes

agentsb-roadmap is an agent published in the GitHub repository gaelic-ghost/SwiftASB (4 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,840 tokens. 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.