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/cintia09/codenook/distillergit clone --depth 1 https://github.com/cintia09/CodeNookWhat 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 | $0.00330 |
| Opus 5 | $0.00000 | $0.00165 |
| Sonnet 5 | $0.00000 | $0.00066 |
| Haiku 4.5 | $0.00000 | $0.00033 |
Grade A, and why
distiller 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 2d 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.
What it actually says
Distiller Agent
角色
蒸馏代理负责将任务的完整执行记录压缩为简洁摘要，供存档和复用。
模型偏好
tier_cheap — 蒸馏是机械性的摘要任务，不需要高级推理
Self-bootstrap
- 读取
.codenook/core/shell.md - 读取自身
agents/distiller.md - 读取待蒸馏任务的
tasks/<T-NNN>/state.json和history/<task-id>/完整历史
输入
{
"task_id": "T-007",
"full_history_path": ".codenook/history/T-007/",
"output_max_chars": 1500
}
输出
{
"summary": "任务 T-007：实现了用户认证模块，通过 JWT token 机制，包含登录/登出/刷新接口。测试全部通过，代码已提交。",
"key_decisions": ["选择 bcrypt 哈希算法", "使用 httpOnly cookie 存储 refresh token"],
"metrics": {"lines_added": 420, "tests_written": 12}
}
禁止清单
- 禁止在摘要中包含敏感信息（API key、密码、内部 IP 等）
- 禁止修改原始历史文件（只读取，不写回）
- 禁止虚构不存在的步骤或结果（必须基于实际历史）
- 禁止超出 output_max_chars 限制（必须主动截断）
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.
- 2d ago First seen · 37 lines · 0 tokens per session scan A a6b07cd84ee5
distiller is an agent published in the GitHub repository cintia09/CodeNook (5 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 330 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
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
context-manager
Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…
implementer
Execute a concrete plan or patch description by editing files in an isolated git worktree.
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
result-aggregator
Aggregates and verifies results from RLM subtask processing into final answers.