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 skills/baek-labs/hames/gonpx skills add baek-labs/hames --skill gogit clone --depth 1 https://github.com/baek-labs/hamesWrote 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/baek-labs/hames/go)<a href="https://agentmods.dev/skills/baek-labs/hames/go"><img src="https://agentmods.dev/badge/skills/baek-labs/hames/go.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 | $0.00016 | $0.00349 |
| Opus 5 | $0.00008 | $0.00175 |
| Sonnet 5 | $0.00003 | $0.00070 |
| Haiku 4.5 | $0.00002 | $0.00035 |
Grade A, and why
go 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 today.
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
Go
Activate only the contract the user selected, execute within its bounds, and collect the required evidence.
Require a task_id. Without one, propose the single READY contract created by this session and wait for confirmation; with zero or multiple candidates, show choices and never select the newest automatically.
Before activation, verify project root, READY state, current-user approval, revision, specification hash, and session availability. Never clear or replace a mismatched pointer automatically.
Immediately before every critical action, show its target, action, and expected impact and obtain a separate explicit confirmation. /ready approval and /go do not replace this confirmation.
Stop if scope must change, a required result cannot be observed, or the contract changes. Record only safe evidence metadata; never store tokens, credentials, raw messages, personal data, or full tool output.
Move to REVIEW only when every required evidence item passes. Present requirement-to-artifact results and limitations, wait for current-user acceptance, then transition through ACCEPTED and archive the same package internally.
Use the bundled runtime/contract.js candidate, activate, confirm-critical, review, and accept commands. Evidence is accepted only from the bundled post-tool hook's observed response; never manufacture or manually mark evidence as passed. Never pass the approval, confirmation, or acceptance flags before the corresponding current-user message.
After creating a remote resource, compare its returned identifier, parent, name, and type with the contract. Stop on mismatch or duplicate creation; attach the generated identifier to evidence and results without changing the specification.
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.
- today First seen · 23 lines · 16 tokens per session scan A ca144fc8626b
go is a skill published in the GitHub repository baek-labs/hames (5 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 349 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 2026-09-04.
Other skills, from other repositories
代码审查员
专业代码审查专家，提供建设性、可操作的反馈，聚焦正确性、可维护性、安全性和性能，而非代码风格偏好。.
release-gate-loop
发版前自动验证闸门——V 验证 + F 修复循环（verdict FAIL → F 改代码 → 跑 audit → V 重验），最大 3 轮直到 PASS。纯只读验证 + 最小修复。.
fresh-eyes-loop
发布后独立质量循环——A/B 双盲 12 视角 fresh-eyes 审查 + 修复 + 验证，每轮新 session 保证零上下文，连续 2 轮无 P0/P1 即停。.
sofagent-fde
前线部署与知识工程专家。梳理企业业务流、识别 AI 节点、构建 ontology 本体数据、交付离场。 部署完成后转为持续优化模式（sustain），自动读 audit 报告趋势生成优化报告。 不写应用代码——把企业业务规则、组织架构、系统边界转译成 sofagent 的数据层和约束层。.
sofagent-audit
收到用户任务后，不要自己执行——用 Bash tool 把任务交给 DeepAgents 编排引擎：.
sofagent
FDE Skill——帮 FDE（前线部署工程师）更好完成企业 AI 落地的方法论 Skill。约束 Agent 行为、审计每次变更、沉淀经验。 底层实现叫约束层——一个层四种能力：注入·审计·回溯·进化。FORGE 自迭代工具链是内部开发工具。 内置持续优化模式（sustain），自动读 audit 报告趋势生成优化报告。.