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/codeinfinity1/stram/focus-and-priority-reviewnpx skills add CodeInfinity1/Stram --skill focus-and-priority-reviewgit clone --depth 1 https://github.com/CodeInfinity1/StramWhat 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 | $0.00044 | $0.00604 |
| Opus 5 | $0.00022 | $0.00302 |
| Sonnet 5 | $0.00009 | $0.00121 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
focus-and-priority-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 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Focus And Priority Review
Purpose
Help the assistant and user choose the next best action from current evidence. This skill maps priority-review concepts to Stram's cognitive priority tools.
When To Use
Use when the user asks "what should I do next", "continue", "prioritize this", "what is important", or when autonomous work needs a bounded next action.
Inputs And Evidence
- Active goals, tasks, and focus from
cognitive_state. - Commitments, wakeups, and recent briefings.
- Environment constraints and current system status.
- User urgency, deadlines, and interruption tolerance.
Tool Map
cognitive_priority_reviewcognitive_priority_statuscognitive_statecognitive_environment_statuscognitive_commitment_statusautomation_daemon_tick
Workflow
- Gather active work and explicit user constraints.
- Identify hard deadlines, blockers, dependencies, and high-risk unresolved items.
- Ask the model to rank next actions from evidence instead of task title similarity.
- Choose one primary focus and at most a few secondary items.
- If autonomous mode is active, queue only one interruptible next action unless explicitly allowed.
- Communicate the reasoning and what will be deferred.
Safety And Boundaries
- Do not bury user-explicit priorities under inferred priorities.
- Do not trigger high-risk work without approval.
- Do not keep cycling priority reviews when the next action is already clear.
Safety And Approval
- Priority review can recommend work, but it cannot authorize high-risk tools, external-visible actions, or durable state changes by itself.
- Preserve explicit user priorities over inferred urgency unless current evidence shows a blocker or safety issue.
- Do not queue autonomous work unless the user allowed initiative or the active goal requires bounded continuation.
- Avoid repeated priority loops that consume time without creating a concrete next action.
Native Implementation Boundaries
- Use Stram priority review/status, cognitive state, environment, commitment, and automation daemon tools.
- The model ranks actions from evidence; deterministic code must not rank by recency, keyword, or static urgency lists.
- Queue/status changes must be visible in native records before claiming the assistant will act later.
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 · 76 lines · 44 tokens per session scan A cd095026183d
focus-and-priority-review is a skill published in the GitHub repository CodeInfinity1/Stram (10 stars, last pushed 22d ago), licensed MIT. It adds 44 tokens to every session and 604 once invoked, about $0.0002 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
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
golden-rss
Use when testing the rss golden build.
omh-code-review
This is a Hermes-native code-review workflow skill.
redteam-web-detail-pack
Routing and boundary guidance for authorized general web application security testing. Use as a web testing router when the attack surface should be dispatched to more specific web vulnerability skills.
android-pentest
安卓应用渗透测试 — APK分析、Hook、自动化测试、运行态驱动、签名恢复、抓包分析.
studio
Architecture Studio control plane — initialize or inspect a studio workspace, create and register projects, or route an architecture/AEC task to the right agent or skill. Use when the user runs /as:studio, asks to set up or open their studio, manage its projects, or describes a task without naming a skill.