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/stringke/std-agent/agents-mdgit clone --depth 1 https://github.com/StringKe/std-agentWhat 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 | $0.00806 | $0.00806 |
| Opus 5 | $0.00403 | $0.00403 |
| Sonnet 5 | $0.00161 | $0.00161 |
| Haiku 4.5 | $0.00081 | $0.00081 |
Grade A, and why
std-agent 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 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.
What it actually says
std-agent
stdagent 是纯 Go CLI,以 .stdai/ 为单一真相源,将 rules、skills、commands、references 和 subagents 转换为 25 个 AI CLI target 的原生配置。本仓库是其源码并用自身规则自举。
结构
cmd/stdagent/:程序入口。internal/cli/、config/、parser/、source/:命令、配置与源文档读取。internal/transformer/:协议层和 target adapter。internal/runner/、writer/、state/、budget/:同步、原子写入、状态和上下文预算。docs/:格式、架构及各 target 的官方证据。
技术栈:Go 1.26、Cobra、BurntSushi/toml、goccy/go-yaml、doublestar、GoReleaser;工具链由 mise 管理。
关键约束
.stdai/standards/是 AI 配置源。生成的CLAUDE.md、AGENTS.md和 target 目录只通过go run ./cmd/stdagent sync更新。- frontmatter、协议或 target 映射属于跨 25 个 target 的兼容性变更,必须对照
docs/format-spec.md、docs/conversion-rules.md和对应docs/targets/证据。 - 多 target 共享同一路径时,内容必须字节一致;
AGENTS.md是 target-neutral 的共享 rules 层,target 专属能力写入各自 sidecar。
Done means
相关回归测试已覆盖,且以下命令通过:
mise run check
go run ./cmd/stdagent sync --no-pull --strict
go run ./cmd/stdagent status
commit-style
Conventional Commits 和安全暂存要求
用户要求 commit 时:
- 格式为 Conventional Commits 1.0.0:
<type>(scope): <description>;scope 与现有模块和提交历史一致。 - breaking change 使用
!和BREAKING CHANGE:。 - 只显式暂存当前任务文件;密钥或
.env类文件先报告,不擅自提交。 - 不添加
Co-Authored-By或 AI 署名。
no-history-rewrite
保护已推送分支和 release tag
- 已推送分支只追加 commit 并 fast-forward push;
main和受保护分支永不 force-push。 - amend 或 rebase 仅限本人独占、尚未共享的 WIP 分支。
- 已推送并触发发布的 tag 不删除;修复使用更高 patch 版本。
test-requirements
核心转换与写入变更必须有针对性回归测试
修改 transformer、runner、writer 或 parser 时,测试必须先复现风险,再证明修复:
- target 或 transformer 变更覆盖 5 种 type 的关键 fanout 和共享路径。
- runner 控制流覆盖相关 flag、首次与重复 sync、prune 和边界保护。
- writer 变更覆盖 unchanged、overwrite 和 atomic 路径。
Done means go test ./...、go test -race ./internal/runner/... 和 mise run check 通过;无法执行的验证标记 UNKNOWN。
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 · 63 lines · 806 tokens per session scan A 06f7300e1a2e
std-agent AGENTS.md is an instructions file published in the GitHub repository StringKe/std-agent (8 stars, last pushed 11d ago), licensed MIT. It adds 806 tokens to every session, about $0.0040 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
lynxprompt-vscode CLAUDE.md
Claude Code instructions for GeiserX/lynxprompt-vscode, covering claude.md — lynxprompt vs code, tech stack, development, architecture and key commands.
lynxprompt-mcp CLAUDE.md
Claude Code instructions for GeiserX/lynxprompt-mcp, covering claude.md — lynxprompt mcp, tech stack, development, run locally and build.
agent-memory-kit CLAUDE.md
Claude Code instructions for awrshift/agent-memory-kit, covering working on memory kit, rules that are easy to get wrong, before committing a change to hooks or skills, docs that must stay true in the same commit and language.
ai-workflow AGENTS.md
Instructions for cunhaax/ai-workflow, covering ai workflow template, rules — non-negotiable, project overview, commands and architecture.
trackly-cli CLAUDE.md
Claude Code instructions for trackly-app/trackly-cli, covering trackly-cli, tech stack, backend production source of truth, directory structure and key commands.
com-example-config-AsyncTestConfig
Instructions for PIsberg/vibetags, covering copilot instructions for asynctestconfig and immutable type.