campaign-conductor SKILL.md skillA
campaign-conductor from jvogan/a-fable-of-codexes is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add jvogan/a-fable-of-codexes/campaign-conductor@v0.11.0Pins v0.11.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- jvogan/a-fable-of-codexes
- Path
skills/campaign-conductor/SKILL.md- Versions recorded
- 10
- Latest version
- v0.11.0, committed Oct 1, 2026
- First version recorded
- Jul 5, 2026
- Size
- 13,590 bytes
- Repository stars
- 55
- License
- MIT
Run a project as an orchestrated campaign: Claude as conductor (Fable 5.1 or Opus 5.5) dispatching OpenAI Codex CLI workers on GPT-6.1 Sol for implementation, each able to run its own team of Sol and Luna leaves, wide GPT-6 Luna sweeps for bulk read-only work, plus Claude Opus 5.5 agents for design judgment and squad leadership and Claude Sonnet 5.5 agents for surveys and search. Use whenever the user says "start a campaign", "campaign mode", "orchestrate this", "use the fleet…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Campaign Conductor You are the conductor, running as the session model: Fable 5.1 at high effort by default, or Opus 5.5 at high when Fable is unavailable or the user chooses it. During a campaign your context window is the scarcest resource in the system: spend it on planning, dispatch, integration judgment, and memory, and let workers spend theirs on surveys, implementation, and routine verification. Read reports, diffstats, and verification tails; open a full diff only where a judgment call needs it. If you start writing feature code during a campaign, stop and dispatch it unless the change is a tiny unblocker. The default fleet has four kinds of direct reports: - **Codex Sol workers** (`gpt-6.1-sol` at `high`) do the implementation. A Sol worker runs a task alone or fans out to a team of leaves through the shipped role files: `feature` and `critic` on Sol, `grunt` on `gpt-6-luna` at `xhigh`. The team is as large as the task splits into disjoint file groups. - **Codex Luna scouts** (`gpt-6-luna`) take bulk read-only work: `xhigh` when many run at once, `max` for a single deep survey. - **Opus 5.5 agents** (`high`, or `xhigh` for hard calls) take design judgment …
Read the whole file at its exact version.
How to install
mdr add jvogan/a-fable-of-codexes/campaign-conductor@sha256:17b8d4a92ebd24baThe line at the top of this page pins the label v0.11.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_p62jevr3ergpbdgq)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 10 versions of this file, between Jul 5, 2026 and Oct 1, 2026, about one every 10 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v0.11.0 latest | 2026-10-01 | 30ce9cb | 13,590 B | A | view · diff |
| v0.10.0 | 2026-09-22 | 2c85f7e | 11,247 B | A | view · diff |
| v0.9.1 | 2026-09-06 | 149554f | 10,700 B | A | view · diff |
| v0.9.0 | 2026-09-06 | a4b53b5 | 10,669 B | A | view · diff |
| v0.8.1 | 2026-09-06 | 53b2812 | 10,100 B | A | view · diff |
| v0.8.0 | 2026-09-05 | fae8692 | 9,613 B | A | view · diff |
| v0.7.0 | 2026-09-01 | 35f6642 | 9,116 B | A | view · diff |
| v0.6.2 | 2026-07-10 | dacf026 | 7,873 B | A | view · diff |
| v0.6.1 | 2026-07-05 | ac58893 | 7,873 B | A | view · diff |
| v0.6.1 | 2026-07-05 | 86b834d | 7,839 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (13590 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
jvogan/a-fable-of-codexes · 55 stars · license MIT · pushed 2026-10-01 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_p62jevr3ergpbdgq GET https://markdownregistry.com/api/v1/resolve?ref=jvogan/a-fable-of-codexes/campaign-conductor GET https://markdownregistry.com/api/v1/blob/17b8d4a92ebd24ba2291e5fdd8cff1ce7c3af7040622ba9de7da4fb6f1a25ba5
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.