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 publish-plangit 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/publish-plan)<a href="https://agentmods.dev/skills/tomzx/agents/publish-plan"><img src="https://agentmods.dev/badge/skills/tomzx/agents/publish-plan/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/publish-plan"><img src="https://agentmods.dev/badge/skills/tomzx/agents/publish-plan.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 | $0.00033 | $0.01260 |
| Opus 5 | $0.00016 | $0.00630 |
| Sonnet 5 | $0.00007 | $0.00252 |
| Haiku 4.5 | $0.00003 | $0.00126 |
Grade A, and why
publish-plan 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Publish Plan
Commits the implementation plan produced by /create-plan to a dedicated branch, opens a draft PR linked to the originating issue, and posts a comment on the issue so the author knows a plan is ready for their review.
Prerequisites
- Apply the shared SDLC conventions in
skills/sdlc/references/shared.md. - If no argument is provided, target the issue from
$ISSUE_NUMBER(and$REPO). ghCLI authenticated with write access to the repository- A reviewed plan file in context or at
$2(defaults to.sdlc/features/N-<slug>/plan.md; falls back toplan.mdin the working directory) - Issue URL or number (
$1) - Clean or committable working tree
Skill attribution (GitHub)
Before posting the issue comment with gh, read github-post-attribution/SKILL.md and append the Posted with footer for SKILL_DIR = publish-plan.
Because publish-plan always runs within the sdlc pipeline, include the SDLC phase footer described in github-post-attribution/SKILL.md (prepend the SDLC phase: plan (<FEAT-id> #<issue>) line above the Posted with line).
Workflow
Read plan file ($2 or plan.md)
|
v
Create branch: plan/<issue-number>
|
v
Commit plan file
|
v
Push branch
|
v
Open draft PR (linked to issue)
|
v
Post comment on issue (links to PR)
Steps
-
Resolve the issue number from
$1:ghx issue view $1Extract the issue number and repository (
owner/repo). -
Determine the plan file path: use
$2if provided, otherwise look for.sdlc/features/N-<slug>/plan.md(where<feature>matches the issue number), then fall back toplan.mdin the current directory. Stop and inform the user if no plan file is found. -
Create and switch to a plan branch:
git checkout -b plan/<issue-number> -
Stage and commit the
.sdlc/features/N-<slug>/directory (which contains requirements, specification, and plan artifacts):git add .sdlc/features/N-<slug>/ git commit -m "docs: add implementation plan for #<issue-number>"
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 · 157 lines · 33 tokens per session scan A a9a32a376ee9
publish-plan is a skill published in the GitHub repository tomzx/agents (6 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 1,260 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 2026-09-03.
Other skills, from other repositories
gsd-quick
Execute a quick task with GSD guarantees (atomic commits, state tracking) but skip optional agents.
gsd-quick-batch
Batch several /gsd:quick-shaped tasks together — planned, dispatched, and merged as one run.
gh-issues
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5]…
gsd-pause-work
Create context handoff when pausing work mid-phase.
gsd-ship
Create PR, run review, and prepare for merge after verification passes.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.