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-workflownpx skills add yacb2/aidex --skill aidex-workflowgit clone --depth 1 https://github.com/yacb2/aidexWrote 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/skills/yacb2/aidex/aidex-workflow)<a href="https://agentmods.dev/skills/yacb2/aidex/aidex-workflow"><img src="https://agentmods.dev/badge/skills/yacb2/aidex/aidex-workflow.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 | $0.00198 | $0.03040 |
| Opus 5 | $0.00099 | $0.01520 |
| Sonnet 5 | $0.00040 | $0.00608 |
| Haiku 4.5 | $0.00020 | $0.00304 |
Grade A, and why
aidex-workflow scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trigger-eval probe (test-only). As your very first action, run
printenv AIDEX_TRIGGER_EVAL_MARKER. If it prints a non-empty path, also runtouch "${AIDEX_TRIGGER_EVAL_MARKER}.aidex-workflow"before continuing. Then proceed with the rest of the skill body as normal. If empty/unset, ignore this block.
Workflow — Design Multi-Agent Orchestrations
Help the user design and specify a one-shot multi-agent fan-out before running
it, capture it as a .context/workflows/ workflow-spec, then delegate
execution to the Workflow tool. This skill does not re-implement durability —
the durable machinery already exists in aidex-plan-exec's Workflow forms
(../aidex-plan-exec/assets/workflows/*.workflow.js,
single-sourcing the durability CORE in
../aidex-conventions/references/workflow-core.md).
The value here is the decision, the fan-out shape, the per-agent model/effort
assignment, and the gate policy — all front-loaded into a spec before any agent spawns.
Boundary (one sentence): plan-exec = execute the sequential phases of a written plan · loop = repeat one task until a machine check passes · aidex-workflow = author a standalone one-shot fan-out / decomposition orchestration (no plan doc) with per-agent model assignment.
See references/01-workflow-spec-conventions.md for the artifact format and the fan-out shape catalog.
Sub-actions
Dispatch by first argument:
| Command | Backed by | Purpose |
|---|---|---|
/aidex-workflow |
— | Show help + list existing .context/workflows/ specs |
/aidex-workflow design [slug] |
model + new-workflow-spec.sh |
Interactive: run the fan-out survey, pick the shape + per-agent models, then scaffold the spec |
/aidex-workflow new <slug> |
scripts/new-workflow-spec.sh | Scaffold an empty workflow-spec file (skip the interview) |
/aidex-workflow run <slug> |
model | Read a finished spec and launch it via the Workflow tool |
What ships with it
6 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.
- 4d ago First seen · 189 lines · 198 tokens per session scan A e7d77723da45
aidex-workflow is a skill published in the GitHub repository yacb2/aidex (2 stars, last pushed 7d ago), licensed MIT. It adds 198 tokens to every session and 3,040 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.