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 Stivi7/cyberpunk-context-runners --skill requirements-discoverygit clone --depth 1 https://github.com/Stivi7/cyberpunk-context-runnersWrote 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/stivi7/cyberpunk-context-runners/requirements-discovery)<a href="https://agentmods.dev/skills/stivi7/cyberpunk-context-runners/requirements-discovery"><img src="https://agentmods.dev/badge/skills/stivi7/cyberpunk-context-runners/requirements-discovery/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/stivi7/cyberpunk-context-runners/requirements-discovery"><img src="https://agentmods.dev/badge/skills/stivi7/cyberpunk-context-runners/requirements-discovery.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 | $0.00024 | $0.01029 |
| Opus 5 | $0.00012 | $0.00515 |
| Sonnet 5 | $0.00005 | $0.00206 |
| Haiku 4.5 | $0.00002 | $0.00103 |
Grade A, and why
requirements-discovery 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 3d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Requirements Discovery
Metadata
- Version: 1.0.0
- Triggers: Direct Fixer invocation or Nexus routing of materially incomplete product work
- Allowed agents: Fixer
- Side effects: Writes and commits one user-approved PRD on the current named branch
When to Use
Use for a new product, feature, or architectural change when the target user, problem, scope, expected behavior, constraints, or acceptance criteria still require material decisions. Do not use for routine fixes, maintenance, a sufficiently specified task, or an approved PRD with no blocking deferred decision.
Inputs
The user's idea, repository context, relevant curated memory, existing specs, applicable decisions, authority boundaries, Git state, and answers gathered during discovery.
Procedure
- Inspect
.cyberpunk/project.md, relevant memory, existing specs, applicable decisions, and current Git state before detailed questions. - Classify the discovery depth:
- Brief: a bounded feature with a known user and outcome.
- Standard: multiple flows or meaningful product decisions.
- Architectural: a new product, cross-system behavior, or major uncertainty.
- If the request contains independently implementable products or subsystems, show their relationships and suggested order, then complete one PRD-sized slice at a time.
- Ask one focused question at a time. Prefer concise choices when they improve clarity, but allow an open answer when the available choices would constrain the user incorrectly.
- Resolve purpose, target users, use cases, goals, measurable success, non-goals, behavior, constraints, authority, risks, and acceptance criteria. Include technical detail only when it is necessary to make a requirement unambiguous; The Mind owns later implementation architecture.
- Present two or three viable approaches with trade-offs and a recommendation.
- Present the requirements in sections proportional to their complexity and request design approval as the design progresses.
- Do not create a PRD until the user has approved the complete design.
- Resolve the PRD path under the literal pattern
specs/YYYY-MM-DD-<topic>-prd.md. The Fixer must not overwrite an existing PRD silently: update it only when the user explicitly identified it, otherwise disclose the conflict and agree on a non-conflicting topic slug. Write the approved PRD with these headings:- Summary and Problem Statement
- Target Users and Use Cases
- Goals and Success Criteria
- Non-goals and Scope Boundaries
- Functional Requirements
- User Journeys and Expected Behavior
- Constraints and Non-functional Requirements
- Considered Approaches and Accepted Decisions
- Edge Cases and Failure Behavior
- Acceptance Criteria
- Dependencies and Risks
- Deferred Decisions
- Self-review for placeholders, contradictions, ambiguous requirements, excess scope, and missing acceptance coverage. A deferred decision records its owner, reason, and resolution stage; it cannot block safe Nexus planning.
- Ask the user to review the written file. Revise and repeat self-review until artifact approval.
- Before committing:
- Confirm
git branch --show-currentreturns the current named branch. - Inspect tracked, untracked, and already staged changes.
- Stage only the approved PRD path without unstaging or modifying unrelated work.
- Verify the PRD diff and use a path-limited documentation commit so unrelated staged paths remain untouched.
- The Git procedure is to commit only the approved PRD.
- Capture the resulting branch and commit SHA.
- Confirm
- Ask whether to hand the committed PRD to Nexus. Do not continue automatically.
- On approval, emit the handoff contract below. On decline, stop with the committed PRD as a successful terminal result.
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.
- 3d ago First seen · 90 lines · 24 tokens per session scan A 259956333a0e
requirements-discovery is a skill published in the GitHub repository Stivi7/cyberpunk-context-runners (4 stars, last pushed 3d ago), licensed MIT. It adds 24 tokens to every session and 1,029 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 2026-09-08.
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.