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 skills/significant-gravitas/autogpt/orchestratenpx skills add Significant-Gravitas/AutoGPT --skill orchestrategit clone --depth 1 https://github.com/Significant-Gravitas/AutoGPTWhat 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 | $0.00078 | $0.09347 |
| Opus 5 | $0.00039 | $0.04673 |
| Sonnet 5 | $0.00016 | $0.01869 |
| Haiku 4.5 | $0.00008 | $0.00935 |
Grade C, and why
orchestrate scanned grade C with 2 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 yesterday.
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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
**Never tell the user "I'll poll every 2-3 minutes"** — that does nothing without a trigger. Start the background job instead. Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat ~/.claude/orchestrator-state.json | jq '.agents[] | {window, worktree, branch, state, pr_number, checkpoints}' The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- scripts/capacity.sh 1.2 KB runs code
- scripts/classify-pane.sh 2.9 KB runs code
- scripts/find-spare.sh 778 B runs code
- scripts/notify.sh 1.3 KB runs code
- scripts/poll-cycle.sh 9.6 KB runs code
- scripts/recycle-agent.sh 1.0 KB runs code
- scripts/run-loop.sh 9.1 KB runs code
- scripts/spawn-agent.sh 5.3 KB runs code
- scripts/status.sh 1.5 KB runs code
- scripts/verify-complete.sh 8.4 KB runs code
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.
- yesterday First seen · 710 lines · 78 tokens per session scan C be0b6a87a3bd
orchestrate is a skill published in the GitHub repository Significant-Gravitas/AutoGPT (187,015 stars, last pushed 2d ago), with no licence file. It adds 78 tokens to every session and 9,347 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (subtle steering, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
final-release-review
Perform pre-release planning or a final release-candidate review for openai-agents-python by comparing the target with the previous remote tag, determining the minimum compatible release type, auditing regressions and contract changes, reviewing open documentation PR coverage, drafting minor-release Key Changes, and…
release-candidate-prep
Preflight and prepare an OpenAI Agents Python release candidate in a dedicated worktree from exact origin/main, gate readiness before branch creation, freeze the released API contract, create or replace the local release branch with one release commit, enforce final release review as a checker, and produce…
implementation-strategy
Choose compatibility-aware scope for runtime and API changes in openai-agents-python. Use before initial implementation and each review-feedback batch to decide whether to patch, reset the design, preserve compatibility, or reject unsupported cases.
pr-draft-summary
Create the required PR-ready summary block, branch suggestion, title, and draft description for openai-agents-python. Use before the final response whenever the current task changed runtime code, tests, examples, build/test configuration, or docs with behavior impact, regardless of perceived change size and including…
examples-run-analysis
Analyze artifacts from the latest completed manual examples Make run. Read the main log, every relevant per-example log, and example source; validate every exit-0 example and classify failures, skips, and environment restrictions. Never execute or control examples.
sensitive-logging-audit
Audit and fix sensitive-data exposure through Python runtime logging in openai-agents-python. Use when reviewing logging, print, warnings, stderr, traceback, MCP names, model or tool exceptions, redaction flags, or any diagnostic path that may retain user data.