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 skills add jmagly/aiwg --skill execution-modegit clone --depth 1 https://github.com/jmagly/aiwgWrote 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/jmagly/aiwg/execution-mode)<a href="https://agentmods.dev/skills/jmagly/aiwg/execution-mode"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/execution-mode/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jmagly/aiwg/execution-mode"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/execution-mode.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00023 | $0.01148 |
| Opus 5 | $0.00012 | $0.00574 |
| Sonnet 5 | $0.00005 | $0.00230 |
| Haiku 4.5 | $0.00002 | $0.00115 |
Grade A, and why
execution-mode 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 9d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execution Mode
You set or report the reproducibility mode that governs how AIWG workflows execute, controlling determinism constraints from none (standard) to fully auditable (audit).
Triggers
Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):
- "make runs deterministic" → set strict mode
- "pin the seed" → set seeded mode with provided seed value
- "what mode are we in" → report current execution mode
- "reset to default" → set standard mode
- "enable audit logging" → set audit mode
Trigger Patterns Reference
| Pattern | Example | Action |
|---|---|---|
| Set standard | "use default execution mode" | Run aiwg execution-mode standard |
| Set seeded | "use a fixed seed for this run" | Run aiwg execution-mode seeded --seed <value> |
| Set strict | "make execution deterministic" | Run aiwg execution-mode strict --seed <value> |
| Set audit | "enable audit mode" | Run aiwg execution-mode audit --seed <value> |
| Status check | "what execution mode is active?" | Run aiwg execution-mode (no args) |
| Seed only | "set seed to 42" | Run aiwg execution-mode seeded --seed 42 |
Behavior
When triggered:
-
Extract intent:
- Is this a status check or a mode change?
- Which mode is requested:
standard,seeded,strict, oraudit? - Is a
--seedvalue provided or should one be generated?
-
Run the appropriate command:
# Report current mode (no args) aiwg execution-mode # Standard — no reproducibility constraints aiwg execution-mode standard # Seeded — fixed random seed for all operations aiwg execution-mode seeded --seed 42 # Strict — seeded + no external calls + pinned versions aiwg execution-mode strict --seed 42 # Audit — strict + decision logging for replay aiwg execution-mode audit --seed 42 -
Mode summary:
Mode Seed External calls Pinned versions Decision log standardNo Allowed No No seededYes Allowed No No strictYes Blocked Yes No auditYes Blocked Yes Yes
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.
- 9d ago First seen · 140 lines · 23 tokens per session scan A 606c70d82ed1
execution-mode is a skill published in the GitHub repository jmagly/aiwg (211 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 1,148 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
surge
Use when a user provides a PRD, spec, or detailed requirements document and needs a full project delivered through iterative expert orchestration — multi-round analyze/research/design/implement/QA cycles with convergence detection. NOT for: single-file edits, quick prototypes, simple Q&A, or tasks without a written…
goal-writer
Drafts a goal+rider document pair that briefs an autonomous coding agent on one round of work — a goal file under 4,000 characters (sized to fit the /goal command in both Claude Code and Codex) plus an unbounded rider with phased plans and named depth tests. Use when the user says "draft a goal", "write a goal+rider"…
horizon
Run a durable Horizon workflow for a multi-feature goal with bounded autonomous retries and an audit trail.
check-in
Record a Parallax protocol checkpoint with concrete evidence before gated implementation work.
debug
Perform an evidence-based Parallax diagnosis or post-build audit and verify the repair.
hyperplan
Harden a non-trivial plan through a three-round adversarial critique and evidence-based synthesis.