github-issue-planning

github-issue-planning is a skill for Claude Code, Codex from soulcodex/agentic. It costs 62 tokens per session (827 once invoked), scanned A, original, MIT.

A skill for saving a work plan on a GitHub issue, the page used to track a piece of work in a repository. It keeps the plan in one marked comment and can use GitHub MCP or the gh command-line tool.

In plain words
What is it for?
It is for planning work tied to a specific GitHub issue, updating that issue's managed plan comment, and falling back to local storage when GitHub persistence is unavailable.
Why use it?
It keeps the plan visible to the team and updates the same comment instead of creating duplicates.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex; mentions OpenCode.

Good fit It is for planning work tied to a specific GitHub issue, updating that issue's managed plan comment, and falling back to local storage when GitHub persistence is unavailable.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/soulcodex/agentic/github-issue-planning
Install

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.

Any agent
npx skills add soulcodex/agentic --skill github-issue-planning
Clone the repo
git clone --depth 1 https://github.com/soulcodex/agentic

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for github-issue-planning

README.md
[![agentmods](https://agentmods.dev/badge/skills/soulcodex/agentic/github-issue-planning/github.svg)](https://agentmods.dev/skills/soulcodex/agentic/github-issue-planning)
Your own site
<a href="https://agentmods.dev/skills/soulcodex/agentic/github-issue-planning"><img src="https://agentmods.dev/badge/skills/soulcodex/agentic/github-issue-planning/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.

agentmods 80×15 button for github-issue-planning

Your own site · 80×15
<a href="https://agentmods.dev/skills/soulcodex/agentic/github-issue-planning"><img src="https://agentmods.dev/badge/skills/soulcodex/agentic/github-issue-planning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 827 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00062 $0.00827
Opus 5.5 $0.00025 $0.00331
Sonnet 5.5 $0.00012 $0.00165
Haiku 4.5 $0.00006 $0.00083

Measured 1mo ago against content hash 159145d1197c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

github-issue-planning 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 1mo 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.

skills/agentic/github-issue-planning/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Issue Planning Skill

Use this skill when planning work tied to a GitHub issue and the plan should be persisted on that issue for team visibility.

Required Input

Do not proceed without one of:

  • Full issue URL (https://github.com/{owner}/{repo}/issues/{number}), or
  • Owner/repo plus issue number ({owner}/{repo}#{number})

If neither is available, ask for it first.

Persistence Contract (Managed Comment)

Persist the plan in one managed issue comment with a stable marker:

<!-- agentic:github-issue-plan -->

Rules:

  • Exactly one managed comment per issue per planning thread.
  • Update that managed comment in place on subsequent runs (idempotent).
  • Keep the marker at the top of the comment body so it is discoverable.
  • Use issue-comment-template.md as the body scaffold.

Decision Tree

  1. MCP path (preferred):
  • If GitHub MCP is available and configured, use MCP issue/comment tools to find existing comments containing <!-- agentic:github-issue-plan --> and update.
  • Enforce deterministic managed-comment handling:
    • 0 matching comments: create one managed comment with marker + plan body.
    • 1 matching comment: update that exact managed comment.
    • More than 1 matching comment: stop and request manual cleanup before updating.
  1. gh CLI fallback (primary fallback, not hard-block):
  • If MCP is unavailable or misconfigured, continue using gh CLI.
  • Check auth first:
gh auth status
  • Create a managed comment:
gh issue comment {issue_number} --repo {owner}/{repo} --body-file /tmp/issue-plan.md
  • Update existing managed comment (find exactly one comment id, then edit):
MATCHED_IDS=$(gh api repos/{owner}/{repo}/issues/{issue_number}/comments --paginate \
  --jq '.[] | select(.body | contains("<!-- agentic:github-issue-plan -->")) | .id')

MATCH_COUNT=$(printf "%s\n" "$MATCHED_IDS" | sed '/^$/d' | wc -l | tr -d ' ')
if [ "$MATCH_COUNT" -gt 1 ]; then
  echo "Multiple managed plan comments found; stop and ask for manual cleanup."
  exit 1
fi

COMMENT_ID=$(printf "%s\n" "$MATCHED_IDS" | sed '/^$/d' | head -n 1)

gh api repos/{owner}/{repo}/issues/comments/$COMMENT_ID \
  --method PATCH \
  --field body="$(cat /tmp/issue-plan.md)"

Read the full file on GitHub · 107 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 1mo ago First seen · 107 lines · 62 tokens per session scan A 159145d1197c

Subscribe to this mod's changes

github-issue-planning is a skill published in the GitHub repository soulcodex/agentic (10 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 827 once invoked, about $0.0002 per session on Opus 5.5. 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.