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 alfredxw/denova --skill configurationgit clone --depth 1 https://github.com/alfredxw/denovaWrote 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/alfredxw/denova/configuration)<a href="https://agentmods.dev/skills/alfredxw/denova/configuration"><img src="https://agentmods.dev/badge/skills/alfredxw/denova/configuration/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/alfredxw/denova/configuration"><img src="https://agentmods.dev/badge/skills/alfredxw/denova/configuration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00037 | $0.01152 |
| Opus 5.5 | $0.00015 | $0.00461 |
| Sonnet 5.5 | $0.00007 | $0.00230 |
| Haiku 4.5 | $0.00004 | $0.00115 |
Grade A, and why
configuration 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 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.
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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configuration
Manage every supported configuration resource through the stable config_read and config_apply tools. Never edit Denova configuration files or internal JSON storage directly.
Required workflow
- For an unfamiliar resource, call
config_readwithoperation=describe. Omitresourceto discover all registered kinds, or provide one kind for its contract. - Call
config_read(operation=list)to resolve the exact ID and scope. Catalogs useitemsplusnext_cursor; continue with the identical request and returned cursor untiltruncated=falsewhen the full catalog matters. Before an update or delete, callconfig_read(operation=get)for the exact ID and retain its latest revision. - Read exactly the relevant reference below with
read({"path":"skill://configuration/references/<file>.md"}). Do not infer a value shape from another resource. - Follow that resource's mutation semantics. Call
config_applyfor exactly one create, update, or delete and use only names returned bydescribe. - For update and delete, copy the latest revision from
config_read; never guess, copy an example placeholder, or reuse a stale revision. Preserve every field or layer section the user did not ask to change.
get accepts any number of IDs. A mixed batch succeeds with existing items, explicit missing_ids, and per-ID failures; an entirely unsuccessful completed batch fails. Large exact reads also return next_cursor. Never treat truncated=true as a complete read.
6. config_apply returns only a compact persistence receipt (resource, operation, id, revision). Read the changed item again and compare the requested fields plus preservation-sensitive fields. Report success only when the effective result matches.
Deletion must be explicitly requested by the user. If a stale-revision conflict occurs, read the current item again, reconcile the requested change with that value, and retry once with the new revision. Do not silently overwrite concurrent changes.
What ships with it
11 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/agent-profile.md 13 KB
- references/automation.md 6.5 KB
- references/event-package.md 6.0 KB
- references/game-planning.md 3.0 KB
- references/image-preset.md 4.2 KB
- references/lore-index.md 5.6 KB
- references/narrative-style.md 5.0 KB
- references/rule-system.md 11 KB
- references/skill.md 5.7 KB
- references/state-system.md 9.1 KB
- references/style-reference.md 3.3 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.
- 3d ago Changed f5bf36fd92a7
- 17d ago Changed · +5 lines · +6 tokens per session 2f3e421eabb4
- 1mo ago First seen · 53 lines · 31 tokens per session scan A 233b2ec56080
configuration is a skill published in the GitHub repository alfredxw/denova (971 stars, last pushed 3d ago), licensed Apache-2.0. It adds 37 tokens to every session and 1,152 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-05.
Other skills, from other repositories
omh-research-department
This is a Hermes-native research-department workflow skill.
omh-agent-board
This is a Hermes-native agent-board workflow skill.
starting-a-new-project
Use when the workspace is empty, has no code, and the user brings a raw project idea. Normally reached via setting-up-a-project; not for an existing project.
omh-github-issue-intake
This is an OMH github-issue-intake workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
omh-operating-rhythm
This is an OMH operating-rhythm workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
omh-product-brief
This is an OMH product-brief workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).