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 tomzx/agents --skill frame-opportunitiesgit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/frame-opportunities)<a href="https://agentmods.dev/skills/tomzx/agents/frame-opportunities"><img src="https://agentmods.dev/badge/skills/tomzx/agents/frame-opportunities/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/tomzx/agents/frame-opportunities"><img src="https://agentmods.dev/badge/skills/tomzx/agents/frame-opportunities.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 | $0.00026 | $0.00502 |
| Opus 5 | $0.00013 | $0.00251 |
| Sonnet 5 | $0.00005 | $0.00100 |
| Haiku 4.5 | $0.00003 | $0.00050 |
Grade A, and why
frame-opportunities 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 5d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frame Opportunities
The convergent end of Discover. Takes problems.md, market.md, and competitors.md and builds an opportunity-solution tree: the desired outcome at the top, opportunities beneath, and candidate solutions under each, scored so the gate can decide what to pursue.
This is the artifact the Discover gate evaluates. A low score here should route back to discovery, not forward to validation.
Prerequisites
- Apply the shared PDLC conventions in
skills/pdlc/references/shared.md. problems.md,market.md, andcompetitors.mdfrom the other Discover skills.
Steps
- State the desired outcome (the customer/business result), not a feature.
- Branch into 3-7 opportunities that could move that outcome. Each opportunity is a lever, not a solution.
- Under each opportunity, list 2-4 candidate solutions (these are provisional — Validate will test the riskiest assumptions, not pick a solution yet).
- Score each opportunity on a transparent rubric: customer value, strategic fit (to
goals.md), reach, and confidence. Record the score, not just a gut ranking. - Recommend the opportunity (or two) to carry into Validate, with the one or two riskiest assumptions called out for testing.
- Write
opportunity-tree.mdto the initiative directory.
Output Format
Use the template at skills/pdlc/templates/initiatives/opportunity-tree.md. Carry the standard initiative frontmatter with phase: discover.
Outcome
If $OUTCOME_YAML is set, emit verdict: drafted plus reason.
Completion Checklist
- Desired outcome stated as a result, not a feature
- Each opportunity is a lever, distinct from the others
- Each opportunity scored on a stated rubric (not just ranked)
- The riskiest assumptions to test are explicitly named for Validate
Next Step
Run the Discover gate via make-decision. On proceed, load map-assumptions to begin Validate. On pivot, return to discover-problems or research-market in revision mode.
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.
- 5d ago First seen · 45 lines · 26 tokens per session scan A b6f44eaa1be0
frame-opportunities is a skill published in the GitHub repository tomzx/agents (6 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 502 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.