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 davidtoby/agent-skills --skill agent-platform-operationsgit clone --depth 1 https://github.com/davidtoby/agent-skillsWrote 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/davidtoby/agent-skills/agent-platform-operations)<a href="https://agentmods.dev/skills/davidtoby/agent-skills/agent-platform-operations"><img src="https://agentmods.dev/badge/skills/davidtoby/agent-skills/agent-platform-operations/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/davidtoby/agent-skills/agent-platform-operations"><img src="https://agentmods.dev/badge/skills/davidtoby/agent-skills/agent-platform-operations.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 | $0.00072 | $0.00479 |
| Opus 5 | $0.00036 | $0.00239 |
| Sonnet 5 | $0.00014 | $0.00096 |
| Haiku 4.5 | $0.00007 | $0.00048 |
Grade A, and why
agent-platform-operations 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Platform Operations
Use this umbrella for operational work on Hermes/OpenClaw/Clawdbot-like agent platforms. If the current task is specifically Hermes Agent setup/configuration, also load the official Hermes skill required by the system.
Core workflow
- Identify platform, checkout path, install method, gateway mode, and current command/error.
- Prefer documented CLIs and config files over ad-hoc edits.
- Before destructive changes, create backups of config/state directories.
- Reproduce with logs enabled; capture exact command, exit code, and relevant log excerpt.
- Apply the smallest fix; then verify by running the affected CLI/gateway/tool path.
- Report changed files, commands run, and rollback path.
Labeled playbooks
Manual update and report
Use when the normal updater hangs or is blocked by approval. Pull/update the checkout, inspect status, run a smoke test, and produce a concise maintenance report.
OpenClaw CLI/docs/cheatsheet
Use docs search and the cheatsheet for exact subcommands and flags; do not invent CLI syntax.
Backups and restore
Archive the platform state directory with exclusions for caches/logs/secrets as appropriate. Verify archive creation and restore instructions.
Cost auditing
Parse local usage logs or provider metrics, summarize spend by model/provider/time, and highlight runaway loops or high-cost patterns.
Memory documentation and self-improvement
Capture stable, reusable lessons in memory/skills; avoid storing transient task progress.
Shield/safety hardening
Treat safety policy/config changes as high-risk: inspect current config, make explicit diffs, and verify behavior.
Feishu approval and websocket stability
For button/callback failures, provide fallback approval paths and inspect callback sync. For websocket reconnect delays or duplicate gateways, check app_id collisions, ping intervals, and running processes.
Reference files
Historical platform-specific recovery recipes and exact errors are stored under references/from-*.md.
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/from-devops-hermes-manual-update-and-report.md 7.2 KB
- references/from-openclaw-imports-auto-updater.md 10.0 KB
- references/from-openclaw-imports-clawddocs.md 8.4 KB
- references/from-openclaw-imports-openclaw-backup.md 3.8 KB
- references/from-openclaw-imports-openclaw-cheatsheet.md 9.5 KB
- references/from-openclaw-imports-openclaw-cost-auditor.md 1.9 KB
- references/from-openclaw-imports-openclaw-memory-docs.md 8.3 KB
- references/from-openclaw-imports-openclaw-shield.md 6.5 KB
- references/from-user-imports-feishu-approval-fallback.md 8.7 KB
- references/from-user-imports-feishu-websocket-stability.md 7.9 KB
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.
- 6d ago First seen · 52 lines · 72 tokens per session scan A 2317473324ff
agent-platform-operations is a skill published in the GitHub repository davidtoby/agent-skills (10 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 479 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
morph-ppt
Use this skill when the user wants a .pptx with smooth cross-slide animation — PowerPoint Morph transitions, Keynote-style continuous motion, shapes that grow / move / rotate as the slide advances. Trigger on: 'morph', 'morph transition', 'smooth transition', 'continuous animation across slides', 'Keynote-style…
officecli-academic-paper
Use this skill to build academic-style .docx output: journal / conference / thesis chapters carrying formal citation style (APA, Chicago, IEEE, MLA), numbered equations, figure & table cross-references, footnotes/endnotes, bibliography, or multi-column journal layout. Trigger on: 'research paper', 'journal paper'…
officecli-word-form
Use this skill to create fillable Word forms (.docx) with real Content Controls (SDT) + legacy FormField checkboxes + MERGEFIELD mail-merge placeholders + document protection. Trigger on: 'fillable form', 'form fields', 'content controls', 'SDT', 'word form', 'fill in', 'only editable fields', 'protect document'…
find-skills
Use when automatically discover, evaluate, and activate community skills when local skills don't cover user needs. Includes credibility scoring and safety checks for complete OpenClaw self-sufficiency.
ehr-analysis
End-to-end EHR predictive modeling pipeline with PyHealth, covering dataset loading, task definition, model training, evaluation, calibration, and clinical interpretation.
protein-design-qc
Protein design quality control, filtering thresholds, and ranking guidance. Use this skill when: (1) Evaluating design quality for binding, expression, or structure, (2) Setting filtering thresholds for pLDDT, ipTM, PAE, (3) Checking sequence liabilities (cysteines, deamidation, polybasic clusters), (4) Creating…