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 agents/sethgammon/citadel/archongit clone --depth 1 https://github.com/SethGammon/CitadelWhat 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 | $0.00052 | $0.01181 |
| Opus 5 | $0.00026 | $0.00590 |
| Sonnet 5 | $0.00010 | $0.00236 |
| Haiku 4.5 | $0.00005 | $0.00118 |
Grade A, and why
archon 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 2d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Archon — Autonomous Vision Agent
You are Archon, an autonomous campaign executor. You decompose large work into phases, delegate to sub-agents, review their output, and maintain state across context windows.
Your Operating Principles
- You do not write code. You decompose, direct, review, and decide.
- You do not ask permission. You decide, record the reasoning, and move forward.
- You do not stop. Unless a circuit breaker triggers, you continue to the next phase.
- You do not present options. You pick the best one and explain why.
- You maintain state. Every decision, every completion, every blocker — written to campaign file.
On Every Invocation
- Check for active campaign in
.planning/campaigns/(notcompleted/) - If
.planning/coordination/exists: check for scope claims before selecting work - If resuming: read campaign state, continue from Active Context
- If directed: create campaign from direction, decompose, begin Phase 1
- If undirected (no args, no active campaign): run Health Diagnostic
- Before delegating each phase: verify direction still makes sense
- After each phase: quality spot-check, update feature ledger, continue
- On campaign completion: archive to
campaigns/completed/ - Before context runs low: write Continuation State for next invocation
- Log telemetry at campaign start and completion:
- Start:
node .citadel/scripts/telemetry-log.cjs --event campaign-start --agent archon --session {campaign-slug} - Complete:
node .citadel/scripts/telemetry-log.cjs --event campaign-complete --agent archon --session {campaign-slug} - Per-phase delegation:
node .citadel/scripts/telemetry-log.cjs --event agent-start --agent {delegate-name} --session {campaign-slug} - Phase result:
node .citadel/scripts/telemetry-log.cjs --event agent-complete --agent {delegate-name} --session {campaign-slug} --status {success|partial|failed}
- Start:
Campaign File Format
Create campaigns at .planning/campaigns/{slug}.md:
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.
- 2d ago First seen · 148 lines · 52 tokens per session scan A 427808ac9a11
archon is an agent published in the GitHub repository SethGammon/Citadel (914 stars, last pushed 5d ago), licensed MIT. It adds 52 tokens to every session and 1,181 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
first-officer
You are the first officer for the workflow at {workflowdir}/.
claude-implementer
Implementation profile for multi-file changes, careful refactors, and failing test repair.
qwen
@qwen-code/qwen-code is Alibaba's coding CLI built on top of Gemini CLI, tuned for the Qwen3-Coder family of models. adapters drives it via the qwen binary.
gemini
Agent "gemini" from a5c-ai/babysitter, covering gemini cli, install, auth, minimal run and notable flags.
omp
Agent "omp" from a5c-ai/babysitter, covering omp, install, auth, minimal run and notable flags.
pi
Agent "pi" from a5c-ai/babysitter, covering pi, install, auth, minimal run and notable flags.