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.
npx agentmods add agents/onehillai/asdd/runtimegit clone --depth 1 https://github.com/OneHillAI/ASDDWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.01928 |
| Opus 5 | $0.00000 | $0.00964 |
| Sonnet 5 | $0.00000 | $0.00386 |
| Haiku 4.5 | $0.00000 | $0.00193 |
Grade A, and why
runtime 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The agent-runtime adapter
ASDD is a standard, so it cannot mandate a model. The runtime, what actually reads a diff and produces a review, is pluggable. The reference workflows call a thin adapter; you choose which one. This neutrality is what lets ASDD be a standard rather than one vendor's tool.
The same holds one layer up, for the operator that runs the agents: bring your own (any operator satisfying this contract), or use the Goose operator kit. The standard mandates neither, "run with your own operator" and "run with Goose" are two supported paths, not a dependency.
pipeline (workflows) → scripts/run-review.sh → runtime adapter → review.json
fixed, audited seam yours data
The pipeline, the policy decision point, the disclosure and merge gates are fixed and the same for everyone. Only the boxed "runtime adapter" varies.
This page is the public contract: enough to build a conforming adapter against. The pipeline code (
run-review.sh, the workflows) and the shipped adapters (generic.sh,openai-compat.sh) live with the reference implementation. Paths below (scripts/runtime/<name>.sh,run-review.sh) describe that bundle's layout; implement the same interface in your own pipeline if you are not running it.
The contract
An adapter is an executable at scripts/runtime/<name>.sh (review) and optionally
scripts/runtime/triage-<name>.sh (triage). Select it with runtime: <name> in .asdd.yml.
Inputs (environment, set by run-review.sh):
| Var | Meaning |
|---|---|
ASDD_WORKDIR |
Directory of untrusted data files: title.txt, body.md, author.txt, changes.diff, meta.env. |
ASDD_OUT |
Path the adapter MUST write the review JSON to. |
ASDD_ROOT |
Repo root (read the fixed lens prompts under agents/). |
ASDD_RUNTIME_TOKEN |
Your runtime credential (model API key, etc.). The only secret the analysis job holds. |
ASDD_MODEL_URL |
The model endpoint (OpenAI-compatible), if the adapter calls one. |
ASDD_MODEL |
Back-compat fallback for the reviewer model. Prefer models.reviewer from .asdd.yml (rule 7). |
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.
- yesterday First seen · 129 lines · 0 tokens per session scan A debcdc48607b
runtime is an agent published in the GitHub repository OneHillAI/ASDD (5 stars, last pushed 20d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,928 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.
Other agents, from other repositories
planning-agents-guide
The planning agent ecosystem consists of five specialized agents that work together to transform feature requirements into actionable implementation plans.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
ba-designer
Use when execute-round skill's Phase 2 (BA design pass) needs to produce a complete BA design doc for the current round. Generates D-1..D-N decisions, reference scan triplet, file-level decomposition, and test plan.
design-reviewer
Design lead + expert design critic. Two modes: Mode A — authors the project's root DESIGN.md (design identity) at project start. Mode B — reviews built UI against DESIGN.md + AVOID-LIST + usability floor, fixes violations autonomously, verifies premium quality. Delegate when: a UI project has no DESIGN.md yet, UI…
Audit
Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…
nodejs-expert
Specializes in Node.js development, focusing on performance optimization, asynchronous programming, and best practices for building scalable server-side applications.