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 dkstm95/hope --skill pr-writinggit clone --depth 1 https://github.com/dkstm95/hopeWrote 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/dkstm95/hope/pr-writing)<a href="https://agentmods.dev/skills/dkstm95/hope/pr-writing"><img src="https://agentmods.dev/badge/skills/dkstm95/hope/pr-writing/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/dkstm95/hope/pr-writing"><img src="https://agentmods.dev/badge/skills/dkstm95/hope/pr-writing.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 | $0.00048 | $0.00669 |
| Opus 5.5 | $0.00019 | $0.00268 |
| Sonnet 5.5 | $0.00010 | $0.00134 |
| Haiku 4.5 | $0.00005 | $0.00067 |
Grade A, and why
pr-writing 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 17d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hope PR Writing
Apply when preparing a PR or MR title and description, whether the person asks directly or the current authorized workflow reaches creation or update. Explicit invocation is also supported. Work in the current conversation under the surrounding task's authority to publish, push, or merge.
Ground the description
Read applicable repository instructions, including AGENTS.md and
CONTRIBUTING.md when present, and the relevant PR or MR template. Check hidden
template locations such as .github and .gitlab/merge_request_templates;
an empty file-search result does not establish that these known paths are absent.
Honor the person's language, scope, and project conventions. Without a project
rule, use a descriptive title and proportionate prose; do not impose Conventional
Commits, a character limit, or mandatory headings. Do not create project settings
just to apply this skill.
Identify the actual proposed change against its target branch. Use the current diff, relevant code, conversation decisions, and observed verification results. Distinguish committed changes from local work that will not be submitted. Use existing PR or MR text as context, then reconcile it with the final change. Resolve scope from available evidence; ask only if remaining ambiguity changes what the description would claim.
Ground the explanation in the concrete problem or purpose, resulting behavior, and evidence a reviewer needs. Include reasoning the diff cannot show and material verification limits. Select further context for the change: before/after evidence, measurements, compatibility or rollout implications, related links, or review focus. Do not infer intent, successful tests, performance gains, or compatibility guarantees from code alone. Use issue-closing keywords only when the submitted change resolves that issue.
Write with Hope Write
Use Hope Write for drafting or editing the title and body through its public contract at Write. Load that skill and follow it in this conversation; use the host's skill invocation mechanism when available. This handoff is permitted without a separate user command. Provide the grounded change, repository format, language, verification evidence, and any review focus. PR Writing owns factual scope and completeness; Write owns clear expression without changing those facts. Do not substitute reading only Write's shared standard for using the skill.
What ships with it
2 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.
- 17d ago First seen · 64 lines · 48 tokens per session scan A 8b55c4e2b3c8
pr-writing is a skill published in the GitHub repository dkstm95/hope (8 stars, last pushed 8d ago), licensed MIT. It adds 48 tokens to every session and 669 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 2026-09-30.
Other skills, from other repositories
conventional-commits
Use when uncommitted changes need to be split into atomic, conventional commits ordered for review. Triggers on "commit this", "make commits", "clean up commits", "commit the changes". In Hedgehog, each Loop step is already meant to be its own commit — this skill matters most when a Correction Protocol fast-forward…
hedgehog-contributing
Use when the user wants to contribute a fix or roadmap item back to the Hedgehog project itself (skyf0xx/hedgehog) rather than their own project. Triggers on "let's fix that in Hedgehog", "I want to contribute", "let's pick up a roadmap item", or when tweaker offers this at the end of a build and the user says yes.…
pr-writing
Use whenever writing a PR title/description, a commit message body, a code review comment, or an issue — in Hedgehog's own repo or any consuming project. Triggers on "open a PR", "write the PR description", "comment on this PR", "file an issue". Covers writing style (terse, info-dense, Simplified Technical English)…
hedgehog-orchestrating
Use at the start of any session on a project with a build graph (.hedgehog/hedgehog.db), and again at every claim/dispatch/verify cycle within it. Owns consuming the build graph — claiming task packets, delegating each to the layer's agent, running hedgehog verify to gate the commit, recording debt and decisions, the…
review
Structured code review with parallel audit agents, confidence-scored triage, and optional auto-fix. Examines uncommitted changes, staged diffs, commit ranges, or specific paths. Produces a tiered report (MUST-FIX / RECOMMENDED / NIT) backed by evidence, then optionally applies fixes with verification.
workflow
Run the complete 5-step development workflow: focus problem → prevent over-development → test-first (TDD) → document → smart commit. Use when starting a new feature, or when the user runs /workflow or asks for the full development flow.