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 Avyayalaya/agent-council --skill strategy-stakes-reviewgit clone --depth 1 https://github.com/Avyayalaya/agent-councilWrote 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/avyayalaya/agent-council/strategy-stakes-review)<a href="https://agentmods.dev/skills/avyayalaya/agent-council/strategy-stakes-review"><img src="https://agentmods.dev/badge/skills/avyayalaya/agent-council/strategy-stakes-review/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/avyayalaya/agent-council/strategy-stakes-review"><img src="https://agentmods.dev/badge/skills/avyayalaya/agent-council/strategy-stakes-review.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00109 | $0.03694 |
| Opus 5 | $0.00055 | $0.01847 |
| Sonnet 5 | $0.00022 | $0.00739 |
| Haiku 4.5 | $0.00011 | $0.00369 |
Grade A, and why
strategy-stakes-review 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 12d 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 — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Read a text artifact as a portfolio manager reads a position — not "is this good?" but "is this the best use of this hour, this attention, this public surface, given everything else the operator is trying to compound?"
The artifact arrives optimized for itself. It survived the operator's own gate. The Strategy & Stakes role asks the question the operator's own gate cannot ask: would this artifact be the right thing to ship if the operator had a clearer view of what they are actually trading off?
The role is not a brake. It is a portfolio overlay. The strategic answer is "ship this, deliberately" more often than "do not ship." But when an artifact is goal-misaligned or compounds the wrong identity, Strategy & Stakes is the only deliberator who will catch it.
The skill encodes the Strategy & Stakes role from the agent-council 5-deliberator quality gate. Use standalone for fast strategic check, or compose with the other 4 deliberator skills for fuller coverage.
When to Use / When NOT to Use
Use this skill when:
- You have a draft Tier-1 artifact and want to confirm it serves the highest-leverage goal before spending the publish hour on it
- You suspect opportunity cost is high (some queued work would compound more than this artifact) and want it named
- You want to surface identity-coherence risk — does this artifact match the operator's executive arc, or does it drift into a positioning the operator does not actually hold?
- Kill-criteria are committed for the project (in
registry.jsonor a strategy doc) and you want them checked before publish - You are running a multi-deliberator review and need the Strategy & Stakes seat filled
Do NOT use this skill when:
- You need a structural critique (load-bearing claims, counter-positions) — use
skeptic-reviewinstead - You need a voice critique (banned patterns, register check) — use
voice-identity-reviewinstead - You need an evidence audit (per-claim tier assignment) — use
evidence-calibration-reviewinstead - You do not have a goals framework loaded — strategic-fit assessment without canonical goals is intuition, not analysis
- The artifact is so low-stakes the strategic overlay would add more cost than value (most internal notes)
- You want to rebuild the operator's strategy from scratch — this skill applies the strategy as committed, not rebuilds it
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.
- 12d ago First seen · 256 lines · 109 tokens per session scan A d596a838131d
strategy-stakes-review is a skill published in the GitHub repository Avyayalaya/agent-council (10 stars, last pushed 1mo ago), licensed MIT. It adds 109 tokens to every session and 3,694 once invoked, about $0.0005 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
multi-agent
Run work across more than one agent — choose between the task subagent, the delegate tool, and a second agentica CLI in tmux driven by peer messages (listagents / sendmessage). Use when a job wants parallel workers, its own terminal, coordination between sessions, or you are choosing among task, delegate, and a second…
web-research
Use this skill for requests related to web research; it provides a structured approach to conducting comprehensive web research.
python-lib-analyzer
Analyze any Python library structure, explore modules, classes, and functions with signatures and documentation.
werewolf-6p
Six-player Werewolf rules for a permanent Agent host, with the user choosing to join the randomized player pool or spectate.
avalon-8-10p
Eight-to-ten-player Avalon rules for a permanent Agent host, with the user choosing to join the randomized player pool or spectate.
execution-orchestrator
A planning and coordination skill for substantial coding tasks. It chooses how work should be organized, tracked, delegated, reviewed, and resumed across execution steps.