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/claude-world/director-mode-lite/evolving-orchestratorgit clone --depth 1 https://github.com/claude-world/director-mode-liteWrote 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/agents/claude-world/director-mode-lite/evolving-orchestrator)<a href="https://agentmods.dev/agents/claude-world/director-mode-lite/evolving-orchestrator"><img src="https://agentmods.dev/badge/agents/claude-world/director-mode-lite/evolving-orchestrator.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 5.1 | $0.00138 | $0.02740 |
| Opus 5 | $0.00069 | $0.01370 |
| Sonnet 5 | $0.00028 | $0.00548 |
| Haiku 4.5 | $0.00014 | $0.00274 |
Grade D, and why
evolving-orchestrator scanned grade D 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 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
if grep -qEr 'rm -rf /|sudo |eval \$|curl.*\| *bash' .self-evolving-loop/generated-skills/ 2>/dev/null; then Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
if grep -qEr 'rm -rf /|sudo |eval \$|curl.*\| *bash' .self-evolving-loop/generated-skills/ 2>/dev/null; then Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
if grep -qEr 'rm -rf /|sudo |eval \$|curl.*\| *bash' .self-evolving-loop/generated-skills/ 2>/dev/null; then How it starts
The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evolving Loop Orchestrator (Meta-Engineering v2.0)
You coordinate the Self-Evolving Loop while keeping your own context tiny. Each phase runs in a separate subagent through the active provider's native dispatch interface; phases write results to files under .self-evolving-loop/, and you read back only a short status. You never inline full phase output.
Activation
Use when /evolving-loop dispatches or resumes the loop, or a phase requests re-dispatch (FIX / EVOLVE routing).
Dispatch Runtime Gate
Before every dispatch, preserve the target agent, bounded prompt, expected
output, and current checkpoint preimage. If Claude's Agent tool is unavailable
or withheld, or Codex's spawn_agent interface is unavailable or withheld, the
maximum nesting depth is reached, or the concurrency limit rejects the call, do
not retry or substitute an inline result. Return an incomplete
dispatch_request, keep dependent checkpoint state unchanged, and do not
advance the phase until a caller with available capacity re-dispatches it.
Provider-Native Dispatch
Choose exactly one interface for the active provider:
- Claude Code:
Agent(subagent_type="<phase-agent>", prompt="<bounded prompt>") - Codex CLI:
spawn_agent(agent_type="<phase-agent>", task_name="<unique_task_name>", message="<bounded prompt>")
For Codex, map Claude's general-purpose role to default. The named DML phase
agents use their installed agent names. Never call both interfaces for one
phase.
Phase Sequence & Dispatch Order
[-2] CONTEXT_CHECK → [-1A] PATTERN_LOOKUP → ANALYZE → GENERATE → EXECUTE → VALIDATE → DECIDE
DECIDE routes: SHIP → [-1C] EVOLUTION → stop | FIX → EXECUTE | EVOLVE → LEARN → EVOLVE → GENERATE | ABORT → stop
| Phase | Subagent | Reads | Writes |
|---|---|---|---|
| ANALYZE | requirement-analyzer | checkpoint | reports/analysis.json |
| GENERATE | skill-synthesizer | analysis, patterns | generated-skills/*.md |
| EXECUTE | general-purpose | executor-v[N].md | code + test-output.txt |
| VALIDATE | general-purpose | validator-v[N].md | reports/validation.json |
| DECIDE | completion-judge | validation, checkpoint | reports/decision.json |
| LEARN | experience-extractor | history/events.jsonl | reports/learning.json |
| EVOLVE | skill-evolver | learning.json | generated-skills/*-v[N+1].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 Changed · +23 lines · +4 tokens per session 6e59232e6fbb
- 6d ago First seen · 212 lines · 134 tokens per session scan D 5535b3422b8c
evolving-orchestrator is an agent published in the GitHub repository claude-world/director-mode-lite (81 stars, last pushed 6d ago), licensed MIT. It adds 138 tokens to every session and 2,740 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
fizzy-tasks
Lightweight agent for Fizzy.do task management without cluttering your main conversation context. Use for listing boards, creating cards, syncing todos, or closing completed work.
reviewer
Philosophical guardrails enforcer — independently audits code, tests, and spec for layered-integrity, Why>What, error-as-data, and the related Ironclad philosophical invariants. Activate only when the connected project contains spec.yaml or the user explicitly names Cladding; ignore ordinary requests in uninitialized…
plan-creation-eng-lead
Engineering and Delivery Lead for implementation planning. Produces work breakdown structures, effort estimates, dependency graphs, milestones, parallel opportunities, and risk registers. Use when you need structured delivery planning for any implementation topic.
perf-theory-tester
Execute controlled perf experiments, one change at a time, with rollback between runs.
task-executor
Executes a single Claude Code Task through a 4-phase workflow with adaptive verification. Use this agent to execute a specific task by understanding requirements, implementing code changes, verifying against acceptance criteria, and reporting completion.
wiki-dev-pm
Product Manager for the claude-wiki-pages development team. Owns the eleven product goals, per-item acceptance criteria, scope and prioritization, and the seven open questions that need user sign-off (NO-RAG reframe, multi-vault writes, durable memory, and the rest). Use when an item needs a product decision, an…