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 instructions/cckyros/goal-acceptance/agents-mdgit clone --depth 1 https://github.com/cckyros/goal-acceptanceWrote 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.
[](https://agentmods.dev/instructions/cckyros/goal-acceptance/agents-md)<a href="https://agentmods.dev/instructions/cckyros/goal-acceptance/agents-md"><img src="https://agentmods.dev/badge/instructions/cckyros/goal-acceptance/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01070 | $0.01070 |
| Opus 5 | $0.00535 | $0.00535 |
| Sonnet 5 | $0.00214 | $0.00214 |
| Haiku 4.5 | $0.00107 | $0.00107 |
Grade A, and why
goal-acceptance AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
goal-acceptance — Project Rules
Package Manager
- Use
pnpm, nevernpmoryarn. - Single package (no workspace).
autoInstallPeers: falseis required:@deepseek-ai/*peer closures include host-platform packages that are not in the npm registry — dsh injects them at runtime.
Architecture
src/plugin/engine/— zero-dependency event-sourced state machine. No Cordis, no Harness, no @deepseek-ai imports.src/plugin/goal-manager.ts— multi-goal manager +FileAcceptanceStoreSessionAcceptanceStore(dsh, type-only imports). Shared by ALL paths.
src/plugin/manifest.ts— SINGLE source of identity (name, version, tools, markers, config). build.mjs generates every identity file from it.src/plugin/tools.ts— 13ToolDefs ({name, description, inputSchema, handler});manifest.toolsis built from them.src/plugin/dsh-plugin.ts— Cordis plugin (service + 13 tools + systemPrompt section + turn-stopping steer + invariant registration).@deepseek-ai/*imports live ONLY here, ininvariant.ts, and type-only ingoal-manager.ts. Plugin id =manifest.name.src/plugin/openclaw-plugin.ts—defineToolPluginport; execute per the SDK contract(params, config, context); id = 'goal-acceptance' (brand).src/plugin/targets/— 22 install adapters (copied framework layer).PLUGIN_PACKAGE_FILESholds exactly 6 entries (deviation #1) — do not change without updating the materialize tests.src/assets/— SKILL.md + 8 companion skills with{{placeholders}}; build syncs them toskills/(deviation #2).
Code Conventions
- TypeScript with
strict(tsconfig in this repo),.tsextension in relative imports,allowImportingTsExtensions. - Event-sourced: all state changes go through
store.append(event)thenapplyEvent(event). applyEventmust be idempotent (sync replays events from the store).- Readonly interfaces for all public types. Mutable state is private inside the engine.
- No TS parameter properties in constructors — node --test strip-only mode cannot parse them (use plain fields).
- Engine errors stay
GoalAcceptanceError(from./engine/index.ts); the framework MCP runtime converts them to{error, code}+isError: true.
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.
- 4d ago First seen · 85 lines · 1,070 tokens per session scan A 8b41f670eb5a
goal-acceptance AGENTS.md is an instructions file published in the GitHub repository cckyros/goal-acceptance (3 stars, last pushed 7d ago), licensed MIT. It adds 1,070 tokens to every session, about $0.0053 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.
Other instructions, from other repositories
working-activity AGENTS.md
AGENTS.md instructions for ccch1mneyyy/working-activity, covering working-activity 项目规则, 用途, pi 版开发约定, dsh 版开发约定 and 文案.
dsh-config-manager AGENTS.md
Instructions for xiajiajun516/dsh-config-manager, covering agents.md — dsh config manager 仓库协作指南, 🗣️ 语言与交流, 📦 项目概览, 🗂️ 仓库结构与职责 and ui 分层(改动前必读,避免放错层).
causal-memory CLAUDE.md
Claude Code instructions for JingxuanC/causal-memory, covering causal memory mcp integration, causal memory integration, after acting on a decision and observing the result, when something fails unexpectedly and when a recorded lesson turns out to be wrong.
dsh-industry-research AGENTS.md
AGENTS.md instructions for PerryLink/dsh-industry-research, covering agents.md, layout, hard rules applied here, checks and release.
dsh-checkpoint-rewind AGENTS.md
AGENTS.md instructions for PerryLink/dsh-checkpoint-rewind, covering agents.md, 仓库布局:发布面 / 本地工程面, 命令, 提交纪律 and dsh 插件约束(红线).
dsh-codex-sync AGENTS.md
Instructions for Walvez/dsh-codex-sync, covering agents.md — dsh-codex-sync, 定位, 怎么跑, 技术栈 and 目录与约定.