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/yacb2/aidex/aidex-loopnpx skills add yacb2/aidex --skill aidex-loopgit clone --depth 1 https://github.com/yacb2/aidexWhat 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 | $0.00206 | $0.02963 |
| Opus 5 | $0.00103 | $0.01482 |
| Sonnet 5 | $0.00041 | $0.00593 |
| Haiku 4.5 | $0.00021 | $0.00296 |
Grade A, and why
aidex-loop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trigger-eval probe (test-only). As your very first action, run
printenv AIDEX_TRIGGER_EVAL_MARKER. If it prints a non-empty path, also runtouch "${AIDEX_TRIGGER_EVAL_MARKER}.aidex-loop"before continuing. Then proceed with the rest of the skill body as normal. If empty/unset, ignore this block.
Loop — Design Agentic Loops
Help the user design and specify an agentic loop before running it, capture it
as a .context/loops/ loop-spec, then hand off execution to an existing
engine. This skill does not implement a loop runner — three mature engines
already exist (/goal, /loop, the ralph-loop plugin) plus headless
claude -p. The value here is the decision, the spec, and the guardrails.
See references/01-loop-engines.md for the engine matrix and guardrails, and references/02-loop-spec-conventions.md for the artifact format.
Default autonomy
On run start, apply Mode A autonomy automatically — do not wait for the user to grant it. Questions live in the initial alignment moment only; after that the run proceeds start-to-finish per the shared canon (deny/pre-authorized/mandated/autonomous). See "Run doctrine" below for how this applies once a loop is running.
Sub-actions
Dispatch by first argument:
| Command | Backed by | Purpose |
|---|---|---|
/aidex-loop |
— | Show help + list existing .context/loops/ specs |
/aidex-loop design [slug] |
model + new-loop-spec.sh |
Interactive: run the loop-suitability questions, pick an engine, then scaffold the spec |
/aidex-loop new <slug> |
scripts/new-loop-spec.sh | Scaffold an empty loop-spec file (skip the interview) |
/aidex-loop run <slug> |
model | Read a finished spec and emit/execute the chosen engine's command |
Dispatch logic
bash "${CLAUDE_SKILL_DIR}/scripts/new-loop-spec.sh" "$@"
What ships with it
7 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.
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 · 196 lines · 206 tokens per session scan A 79d4614ec785
aidex-loop is a skill published in the GitHub repository yacb2/aidex (2 stars, last pushed 5d ago), licensed MIT. It adds 206 tokens to every session and 2,963 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
autoprompt
Explicit-only useful-first orchestration. Invoke only when the user names autoprompt - typed as /autoprompt or in plain language such as "act in autoprompt mode" - to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Do not infer invocation from…
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
autoprompt
Run the Autoprompt orchestration loop on Prime Agent through a topology-enforcing native RLM dispatcher. Use only when the user explicitly invokes Autoprompt or asks to run the loop.