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 skills add kakadeka/Baton --skill baton-debtgit clone --depth 1 https://github.com/kakadeka/BatonWrote 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/skills/kakadeka/baton/baton-debt)<a href="https://agentmods.dev/skills/kakadeka/baton/baton-debt"><img src="https://agentmods.dev/badge/skills/kakadeka/baton/baton-debt/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kakadeka/baton/baton-debt"><img src="https://agentmods.dev/badge/skills/kakadeka/baton/baton-debt.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00069 | $0.00475 |
| Opus 5 | $0.00034 | $0.00237 |
| Sonnet 5 | $0.00014 | $0.00095 |
| Haiku 4.5 | $0.00007 | $0.00047 |
Grade A, and why
baton-debt 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 9d 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
baton-debt（技术债扫描，只读）
标记格式（代码内写入时的强制格式）
BATON-DEBT: task=<id>; ceiling=<上限>; revisit_when=<可测触发器>; upgrade=<升级路径>
task：关联任务 ID（无则none）。ceiling：已知上限（如「目录 ≤ 500 文件」「单文件 ≤ 3MB」）。revisit_when：可测触发器（如「E2E 用例超过 60」「文件超过 3MB」）；禁止「以后有空」「未来可能」。upgrade：升级路径（改什么、为什么现在不做）。
扫描与输出
- 搜索代码库全部
BATON-DEBT:标记。 - 每条提取 task/ceiling/revisit_when/upgrade/位置，输出：
文件:行号 | task | ceiling | revisit_when | upgrade | 状态(no-trigger=缺可测触发器)
- 无触发器的标记标
no-trigger并要求补正。 git blame只作线索，不自动认定责任人。
持久化（需要落库时）
- 进入 Baton 现有
tasks/task_todo.md（新增债务条目）或追加到knowledge/pit_experience.md并同步索引； - 自动维护
state/archive_index.json索引——不另建第二套项目真相。
边界
- 只读扫描；修改代码必须先过任务 Contract 与用户确认。
- 债务标记是显式声明，不是放纵理由：标记的 ceiling 到达 revisit_when 时按 upgrade 路径执行。
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.
- 9d ago First seen · 40 lines · 69 tokens per session scan A cd4c8784e61c
baton-debt is a skill published in the GitHub repository kakadeka/Baton (4 stars, last pushed 8d ago), licensed Apache-2.0. It adds 69 tokens to every session and 475 once invoked, about $0.0003 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 skills, from other repositories
context
CONTEXT: Cognitive Order Normalized in Transformer EXtract Truncated. Cross-model context handoff via Progressive Density Layering, MLDoE expert compression, Japanese semantic density, and Negentropic Coherence Lattice validation. Creates portable carry-packets that transfer cognitive state between AI sessions. Use…
distill-habits
Review recent Claude Code conversations, distill the user's stable habits and preferences, persist them into a long-term habit ledger, and maintain a "My Habits" block in the global CLAUDE.md within a character budget. The more you use Claude Code, the more it knows you. Trigger manually with /distill-habits, or on a…
project-state-governor
Maintain evidence-backed project state across conversations, branches, reviews, and research cycles. Use when an AI coding agent must reconstruct or consolidate fragmented project documentation, reconcile conflicting history against code/tests/contracts/Git, classify active and completed work, verify completion…
atomicmemory
Persistent semantic memory across Claude Code sessions — user preferences, project context, prior decisions, codebase facts. Call memorysearch before answering questions that reference past work. Call memoryingest after the user shares durable facts.
atomicmemory-cli
Use the installed AtomicMemory CLI for memory search, ingestion, packaging, diagnostics, and agent-safe JSON output.
memseek-remember
Persist a user-confirmed fact, preference, constraint, or decision in Memseek project memory.