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/jakkaj/tools/plan-2b-v2-prep-issuenpx skills add jakkaj/tools --skill plan-2b-v2-prep-issuegit clone --depth 1 https://github.com/jakkaj/toolsWrote 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/jakkaj/tools/plan-2b-v2-prep-issue)<a href="https://agentmods.dev/skills/jakkaj/tools/plan-2b-v2-prep-issue"><img src="https://agentmods.dev/badge/skills/jakkaj/tools/plan-2b-v2-prep-issue.svg" alt="Measured on agentmods" 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 | $0.00040 | $0.02246 |
| Opus 5 | $0.00020 | $0.01123 |
| Sonnet 5 | $0.00008 | $0.00449 |
| Haiku 4.5 | $0.00004 | $0.00225 |
Grade A, and why
plan-2b-v2-prep-issue 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 6d 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 — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Please deep think / ultrathink as this is a complex task.
plan-2b-v2-prep-issue
Generate concise, well-structured issue text from the feature specification and plan artifacts. This command creates terse, actionable issue content suitable for any issue tracker (GitHub, Azure DevOps, Jira, etc.).
Purpose: Extract clarity from complex specs. The issue is a signpost, not a replacement for the spec.
🚫 NO TIME ESTIMATES
Use Complexity Score (CS 1-5) only — no hours, days, or story points.
User input:
$ARGUMENTS
# Optional flags:
# --phase N # Generate Story/Task level issue for phase N (requires /the-flow 5 output)
# --type TYPE # Override auto-detected type: feature|story|task
## Workflow
1) **Resolve plan folder and artifacts**:
- Parse user input for plan folder path or feature slug
- PLAN_DIR = `docs/plans/<ordinal>-<slug>/`
- Locate available artifacts:
* SPEC_FILE = `${PLAN_DIR}/<slug>-spec.md` (REQUIRED)
* PLAN_FILE = `${PLAN_DIR}/<slug>-plan.md` (optional)
* TASKS_DIR = `${PLAN_DIR}/tasks/` (optional)
- If SPEC_FILE not found: ERROR "Spec not found. Run /the-flow 1b first."
2) **Load domain context** (additive — skip if no domains):
- If `docs/domains/registry.md` exists → read registered domains
- If `docs/domains/domain-map.md` exists → read domain topology
- Read `## Target Domains` from SPEC_FILE (if present) → DOMAIN_LIST
- If PLAN_FILE exists → read `## Target Domains` and `## Domain Manifest` tables
- For each domain in DOMAIN_LIST → read `docs/domains/<slug>/domain.md` for:
* Concepts, contracts, dependencies
- Identify CROSS_DOMAIN_DEPS: domains that depend on each other per domain map
- HAS_DOMAINS = true if any domain info found, false otherwise
3) **Determine issue type** (auto-detect or use --type flag):
- If --phase N provided AND `${TASKS_DIR}/phase-N-*/tasks.md` exists:
* TYPE = story (or task if --type task)
* PHASE_DOSSIER = the tasks.md file
- Else if PLAN_FILE exists:
* TYPE = feature (plan context available)
- Else:
* TYPE = feature (spec-only)
4) **Extract content from artifacts**:
**From SPEC_FILE** (always read):
- TITLE = H1 heading text
- SUMMARY = ## Summary section (2-3 sentences)
- GOALS = ## Goals section (bullet points)
- NON_GOALS = ## Non-Goals section (bullet points)
- AC = ## Acceptance Criteria section (numbered list)
- COMPLEXITY = ## Complexity section (CS score and breakdown)
- RISKS = ## Risks & Assumptions section (key risks only)
- TARGET_DOMAINS = ## Target Domains section (if present)
**From PLAN_FILE** (if exists and TYPE = feature):
- CRITICAL_FINDINGS = top 3 from Key Findings section
- PHASE_COUNT = number of Implementation Phases
- ADR_REFS = any ADR references
- DOMAIN_MANIFEST = ## Domain Manifest table (file → domain mapping)
**From PHASE_DOSSIER** (if TYPE = story/task):
- PHASE_TITLE = Phase heading
- PHASE_OBJECTIVE = from context brief / Purpose
- PHASE_TASKS = task count from tasks table
- PHASE_AC = derive from task Success Criteria column (observable outcomes)
- PHASE_DOMAIN = Domain column from task table (primary domain for this phase)
5) **Generate issue content**:
**For TYPE = feature**:
```markdown
# [TITLE]
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.
- 6d ago First seen · 284 lines · 40 tokens per session scan A 8f86d75518f5
plan-2b-v2-prep-issue is a skill published in the GitHub repository jakkaj/tools (5 stars, last pushed 20d ago), licensed MIT. It adds 40 tokens to every session and 2,246 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…