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 hmj1026/dhpk --skill merge-prepgit clone --depth 1 https://github.com/hmj1026/dhpkWrote 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/hmj1026/dhpk/merge-prep)<a href="https://agentmods.dev/skills/hmj1026/dhpk/merge-prep"><img src="https://agentmods.dev/badge/skills/hmj1026/dhpk/merge-prep/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/hmj1026/dhpk/merge-prep"><img src="https://agentmods.dev/badge/skills/hmj1026/dhpk/merge-prep.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 | $0.00068 | $0.00533 |
| Opus 5.5 | $0.00027 | $0.00213 |
| Sonnet 5.5 | $0.00014 | $0.00107 |
| Haiku 4.5 | $0.00007 | $0.00053 |
Grade A, and why
merge-prep 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 yesterday.
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.
What it actually says
Merge Prep
Workflow
Require <source-branch> and resolve --target to {TARGET_BRANCH} or
main when omitted. Validate both refs and a clean worktree before analysis.
Use native, read-only Git evidence: merge-base, commit log, changed-file
summary, and git merge-tree --write-tree <target> <source> (or report
UNAVAILABLE when the installed Git cannot provide that read-only operation).
Report commits, files, conflict details, likely conflict patterns, and
text-only resolution strategies. Emit copy-pasteable commands for a human to
execute later. Never run git checkout, git switch, git merge, git rebase, or a conflict edit. See
references/workflow.md for the exact sequence.
When NOT to Use
- The worktree is dirty or either branch/ref is missing.
- A merge, checkout, rebase, or conflict resolution should happen now.
- A write-capable branch operation is requested.
Output
Pre-merge evidence includes source/target refs, merge-base, commits, files,
merge-tree output, conflict status, and copy-pasteable manual commands.
Conflicts are findings, not permission to mutate. A complete read-only
analysis ends PASS (with its conflict status); missing preconditions or
unexpected Git failures are terminal BLOCKED/FAIL results. No merge claim
is made.
Verification
- Source and target resolve and
git status --porcelainis empty. - Native merge-tree analysis ran without changing the worktree.
- Commit/file/conflict evidence is included, including clean conflicts when none were found.
- Suggested merge commands are output only and were not executed.
References
references/workflow.md— native analysis, conflict interpretation, and manual command output.
What ships with it
3 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.
- yesterday Changed · +2 lines 19f622dcd1fd
- 23d ago First seen · 52 lines · 68 tokens per session scan A 7d32a861ba0d
merge-prep is a skill published in the GitHub repository hmj1026/dhpk (2 stars, last pushed today), licensed MIT. It adds 68 tokens to every session and 533 once invoked, about $0.0003 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 2026-09-24.
Other skills, from other repositories
add-teams
Adds Microsoft Teams connector to a Power Apps code app. Use when sending Teams messages, posting to channels, or integrating with Teams chat.
relations
OPS on-demand: This skill should be used when the user asks to "who do I owe a reply", "relationship…
alive:world
The human doesn't know what to work on, or wants to see everything at once. They need the big picture — what's active, what's stale, what needs attention. Renders a live world view grouped by ALIVE domain, then routes to open, tidy, find, history, or map.
figure-out
Figure things out together — any topic, problem, or idea. Presses relentlessly until shared understanding is reached. Use when understanding is the deliverable rather than a preamble to acting, when figuring it out is the goal, or when the user asks to think through a decision, dig deeper, press an assumption…
cli
Type-safe CLI argument parsing with commander and @commander-js/extra-typings, the standard parser for this repo's Bun scripts. Use when writing or editing any script that takes arguments (flags, positional parameters, subcommands, nested subcommands, --help) instead of reading existing scripts for the pattern.
promote
Turn a scratch script into a permanent tool this repo keeps. Use when a check, report, or analysis has proved worth running more than once.