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/slowdoctor-dev/workspace-md/detect-runtimenpx skills add slowdoctor-dev/workspace-md --skill detect-runtimegit clone --depth 1 https://github.com/slowdoctor-dev/workspace-mdWrote 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/slowdoctor-dev/workspace-md/detect-runtime)<a href="https://agentmods.dev/skills/slowdoctor-dev/workspace-md/detect-runtime"><img src="https://agentmods.dev/badge/skills/slowdoctor-dev/workspace-md/detect-runtime.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 | $0.00066 | $0.03254 |
| Opus 5 | $0.00033 | $0.01627 |
| Sonnet 5 | $0.00013 | $0.00651 |
| Haiku 4.5 | $0.00007 | $0.00325 |
Grade C, and why
detect-runtime scanned grade C with 3 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 3d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -s http://localhost:11434/api/show -d '{"name":"<model>"}' | jq '.parameters' Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| `~/.continue/config.yaml` | `continue` | Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://localhost:11434/v1/models # Ollama How it starts
The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
detect-runtime
When to use
- From
init— bootstrap; produce initial profile.md draft for Owner ratify fromprofile.example.md - From
session-start— cheap re-detect every session; compare against active profile.md when present; propose re-ratify on drift - Explicit
/detect-runtime— Owner invocation after switching harness or backend - From
audit(rare) — freshness re-check oflast_verifiedconstants
Requires
Requires 3-control/foundation/SOUL.md,
3-control/foundation/PRINCIPLE.md, and 2-mind/garden/essential/
to exist. If any are missing, run init instead of continuing.
Operationalizes the detection mechanism described in
3-control/foundation/runtime-flexibility.md §Detection mechanism.
Quick reference
Single principle: the running agent IS the runtime instance — agent self-introspection is the primary signal; objective signals (env vars, config files, endpoint queries) cross-check. Mismatch = report to Owner; never silently resolve.
Harness is an open enum. Known values:
claude-code, codex-cli, gemini-cli, antigravity, cursor,
hermes, opencode, continue, custom.
| Sub-step | Primary signal | Verification | Fallback |
|---|---|---|---|
| 1. Harness | Agent self-introspection | Env var → repo config folder → user-level config | custom |
| 2. Backend (provider + endpoint + model) | Agent self-identification | Per-harness config read; if local-via-proxy, probe localhost ports for /v1/models |
Ask Owner |
| 3. Effective context | Agent self-knowledge | Hosted: known-constants table (below); Local: /v1/models response + attention-cliff clamp |
Owner declaration |
Optional helper: 2-mind/forge/act/script/detect-runtime.sh
automates objective verification only: Sub-step 1B/C/D, Sub-step
2B/C, Sub-step 3C (local endpoint) only, then Step 4 tier derivation
and Step 5 JSON emission. Hosted Sub-step 3B is the agent's
cross-check against the SKILL known-constants table, not scripted. The
helper cannot perform Step 0 / Sub-step A agent self-introspection.
The running agent supplies that primary signal before interpreting the
helper output.
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.
- 3d ago First seen · 290 lines · 66 tokens per session scan C bf9fa22bbb25
detect-runtime is a skill published in the GitHub repository slowdoctor-dev/workspace-md (1 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 66 tokens to every session and 3,254 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 3 findings (sends data to an external url, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
skill-ledger
Skill 安全状态查看、风险暴露审查、用户决策、快速扫描认证与可选深度扫描。支持用户主动查看或扫描单个/全部 Skill；当用户要求 agent 安装 Skill 且安装成功后，必须自动对最终本地目录执行快速扫描认证。.
regex-mastery
Use this skill when writing regular expressions, debugging pattern matching,optimizing regex performance, or implementing text validation. Triggers on regex, regular expressions, pattern matching, lookahead, lookbehind, named groups, capture groups, backreferences, and any task requiring text pattern matching.
install-openclaw
Install and configure OpenClaw non-interactively with Alibaba Cloud Model Studio. Use when the user asks to install OpenClaw, configure Aliyun Bailian/Model Studio/DashScope credentials, choose pay-as-you-go, Coding Plan, or Token Plan billing, set Base URL/model config, optionally configure DingTalk, start the local…
ws-ckpt
工作区快照管理。用户说"保存一下"、"存个快照"时创建 checkpoint，仅限 Linux; 说"回滚"、"撤销"、"恢复到之前"时 rollback;说"删掉快照"时 delete; 说"对比快照"、"快照改了什么"时 diff; 说"看看快照"、"有哪些快照"时 list;说"查看快照状态"、"查看快照剩余空间"时 status。.
image-gen
Generate images from text prompts via DashScope/Qwen. Use when creating, drawing, or illustrating images.
pdf-reader
Extract text from PDF files. Use when reading, parsing, or analyzing PDFs.