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 commands/theseussss/roamfound/setupgit clone --depth 1 https://github.com/theseussss/roamfoundWhat 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 | $0.00026 | $0.01407 |
| Opus 5 | $0.00013 | $0.00704 |
| Sonnet 5 | $0.00005 | $0.00281 |
| Haiku 4.5 | $0.00003 | $0.00141 |
Grade A, and why
setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
jiacong-flow · 同步多 CLI 入口
Claude Code 模式把 plugin 里 protocol-fragments/ 下的 8 个 fragment（identity-check / env-verify / startup-align / language / interaction-protocol / map-feedback / edit-levels / jailbreak）注入用户级 ~/.claude/CLAUDE.md。
Codex 模式把 jiacong-flow 全局入口注入 ~/.codex/AGENTS.md，并把 skills/*/ 下的并列 skills 安装到 ~/.codex/skills/<skill-name>。
Gemini CLI 模式把 jiacong-flow 全局入口注入 ~/.gemini/GEMINI.md，并把 skills/*/ 下的并列 skills 安装到 ~/.gemini/skills/<skill-name>。
Hermes Agent 模式把 jiacong-flow 协议片段注入 ~/.hermes/SOUL.md，把自包含插件链接到 ~/.hermes/plugins/jiacong-flow。Hermes hooks 由插件 plugin.yaml 声明，不额外写用户级 hook 配置。
职责边界
/jiacong-flow:setup 只负责同步 CLI 入口。Claude Code 的命令补全与 skill 入口由 .claude-plugin/plugin.json 的 commands / skills 声明负责；如果输入 /jia 看不到候选，先更新并重载插件，再运行 setup。
执行
Claude Code 默认（实际写入）：
python "${CLAUDE_PLUGIN_ROOT}/install.py" --agent claude
预览（只报告变更不写文件）：
python "${CLAUDE_PLUGIN_ROOT}/install.py" --agent claude --dry-run
指定目标文件（非默认路径）：
python "${CLAUDE_PLUGIN_ROOT}/install.py" --agent claude --target <path>
Codex 全局入口：
# 在 plugin 根目录执行
python install.py --agent codex --dry-run
python install.py --agent codex
# 在 Claude Code plugin command 上下文执行
python "${CLAUDE_PLUGIN_ROOT}/install.py" --agent codex --dry-run
python "${CLAUDE_PLUGIN_ROOT}/install.py" --agent codex
Gemini CLI 全局入口：
python install.py --agent gemini --dry-run
python install.py --agent gemini
python "${CLAUDE_PLUGIN_ROOT}/install.py" --agent gemini --dry-run
python "${CLAUDE_PLUGIN_ROOT}/install.py" --agent gemini
Hermes Agent 全局入口与插件：
python install.py --agent hermes --dry-run
python install.py --agent hermes
python "${CLAUDE_PLUGIN_ROOT}/install.py" --agent hermes --dry-run
python "${CLAUDE_PLUGIN_ROOT}/install.py" --agent hermes
多 CLI 同步：
python install.py --agent claude,codex,gemini,hermes
python install.py --agent all --dry-run
python install.py --agent all
python install.py --list-agents
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 · 120 lines · 26 tokens per session scan A 184bab7dca9d
setup is a command published in the GitHub repository theseussss/roamfound (5 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 1,407 once invoked, about $0.0001 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.