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/eestevanell/codex-planning-kit/create-issue-card-execplannpx skills add EEstevanell/codex-planning-kit --skill create-issue-card-execplangit clone --depth 1 https://github.com/EEstevanell/codex-planning-kitWrote 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/eestevanell/codex-planning-kit/create-issue-card-execplan)<a href="https://agentmods.dev/skills/eestevanell/codex-planning-kit/create-issue-card-execplan"><img src="https://agentmods.dev/badge/skills/eestevanell/codex-planning-kit/create-issue-card-execplan.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 | $0.00079 | $0.01201 |
| Opus 5 | $0.00039 | $0.00600 |
| Sonnet 5 | $0.00016 | $0.00240 |
| Haiku 4.5 | $0.00008 | $0.00120 |
Grade A, and why
create-issue-card-execplan 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 4d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Issue Card + ExecPlan
Purpose
Draft an issue card and (when non-trivial) an ExecPlan that a complete novice can implement end-to-end with no ambiguity, no missing steps, and minimal regression risk. Optimize for correctness, maintainability, and low blast radius.
Inputs (required)
- A brief describing the work (bug/feature/refactor), including desired user-visible outcome.
If the brief is missing critical details, ask only the minimum clarifying questions needed to eliminate ambiguity (see “Minimum clarifying questions”).
Minimum clarifying questions (ask only if needed)
- What is the exact user-visible outcome (one sentence), and how do we see it working?
- What is broken/missing today (current behavior), and how do we reproduce/observe it (URLs, API routes, inputs)?
- Any hard constraints (must not change X, must keep contract Y, deadline/risk sensitivity)?
If the user cannot answer (or for speed), resolve by investigating the repo and recording evidence in the card.
Procedure
- Read repo rules and templates:
AGENTS.mdPLANS.mdissues/README.mdissues/ISSUE_CARD_TEMPLATE.md
- Pick filenames (keep consistent with repo conventions):
- Issue card (preferred once numbered):
issues/open/<number>-<type>-<kebab-summary>.md - ExecPlan:
issues/execPlans/<number>-<type>-<kebab-summary>_execplan.md - If blocked on a number, use
issues/open/draft-<type>-<kebab-summary>.mdandissues/execPlans/draft-<type>-<kebab-summary>_execplan.md, and note in both files that a rename is required aftergh md-issues push.
- Issue card (preferred once numbered):
- Investigate prior art (do not guess):
- Search
issues/**for similar work. - Identify the likely module(s) and exact file paths.
- Capture concrete evidence (errors, logs, stack traces, screenshots, failing test output) as text in the issue card.
- Search
- Draft the issue card (authoritative spec):
- Start from
issues/ISSUE_CARD_TEMPLATE.md; keep headings intact. - Fill every section; use “None.” instead of leaving blanks.
- Include exact strings/contracts when they matter (route paths, error messages, queue names, status values).
- Make blast radius explicit in
Expected Files/Areasand call out high-risk files (e.g.,Program.cs) with rationale. - Set
## StatustoProposed.and keep YAML frontmatter accurate (title,labels,state). - Reference the ExecPlan path at the top (
ExecPlan: issues/execPlans/<slug>_execplan.md).
- Start from
- Decide whether an ExecPlan is required:
- Required when the change is complex, cross-cutting, risky, or spans multiple modules (default to “yes” if unsure).
- For tiny/local changes, the card can stand alone; explicitly justify why an ExecPlan is unnecessary.
- Draft the ExecPlan (novice-executable spec):
- Follow
PLANS.mdstrictly. - The ExecPlan file should contain only the plan (no outer triple-backtick fence).
- Never use nested triple-backtick fences inside the plan; use indented snippets for commands/transcripts/code.
- Define every non-obvious term in
Context and Orientation(if you can’t define it, don’t use it). - Make TDD explicit: name the exact test file(s), test name(s), and the red/green transition.
- Include explicit file paths and insertion points (type/method/component/template names).
- When adding/changing interfaces/contracts, include an
Interfaces and Dependenciessection with explicit signatures and dependencies. - Prefer the simplest design that meets requirements; when multiple approaches exist, pick the best maintainability-to-risk ratio and record the rationale in
Decision Log. - Reuse repo patterns and centralize shared literals (queue names, log templates, status codes, error strings) in the module-appropriate location instead of duplicating strings.
- Include short indented snippets for the most error-prone bits (contracts, signatures, route strings, example test cases, expected outputs).
- Include concrete commands and expected outputs (short transcripts) for build/tests.
- Include rollback/recovery and idempotence guidance.
- Follow
- Junior-proof quality gate (before finalizing files):
- Remove any “TBD”, “should”, “maybe”, “etc.” where it hides a decision.
- Ensure every requirement maps to an acceptance criterion and a verification step.
- Ensure no hidden knowledge: a new engineer can run the listed commands and recognize success/failure.
- Ensure the plan does not smuggle implementation via “follow existing patterns” without pointing to the exact pattern file(s).
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 79 lines · 79 tokens per session scan A e5b1a67af404
create-issue-card-execplan is a skill published in the GitHub repository EEstevanell/codex-planning-kit (2 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 79 tokens to every session and 1,201 once invoked, about $0.0004 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…