Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Jamie-BitFlight/claude_skills/plugin install dhWrote 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/jamie-bitflight/claude_skills/gate-push)<a href="https://agentmods.dev/skills/jamie-bitflight/claude_skills/gate-push"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/gate-push.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 5.1 | $0.00036 | $0.00858 |
| Opus 5 | $0.00018 | $0.00429 |
| Sonnet 5 | $0.00007 | $0.00172 |
| Haiku 4.5 | $0.00004 | $0.00086 |
Grade A, and why
gate-push 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gate Push
Run /dh:gate-push <branch-name> to resolve branch context into a /dh:complete-implementation input and execute that quality-gate pipeline.
Required input
branch_name = $ARGUMENTS(must be non-empty)
If empty: stop with:
COMPLETION BLOCKED — Missing required argument <branch-name>.
Then re-run:
/dh:gate-push <branch-name>
Branch → backlog lookup algorithm
- Normalize
branch_nameinto a lookup slug:- Strip leading branch type prefix when present (
feature/,fix/,chore/, etc.) by removing only the prefix up to and including the first/character - Then replace any remaining
/,_, and-with spaces (for examplefeature/auth/login-fix→auth login fix) - Trim whitespace
- Store the result as
normalized_slug - Expected pattern is
type/slug(e.g.,feature/foo-bar); multi-segment branches (type/segment1/segment2) are supported and normalize with the same replacement rule
- Strip leading branch type prefix when present (
- Strategy 1 (title match):
uv run "${CLAUDE_PLUGIN_ROOT}/sam_schema/cli.py" backlog list --title "<normalized_slug>"
- Strategy 2 (topic match fallback, only if Strategy 1 has zero results):
uv run "${CLAUDE_PLUGIN_ROOT}/sam_schema/cli.py" backlog list --topic "<normalized_slug>"
- If exactly one item is returned, use it as
match. - If multiple items are returned, do not guess — stop and follow the No-match / unresolved fallback procedure below.
Resolve complete-implementation input
From match, resolve in this order:
- If
match.issueexists (issue number field from backlog output) →target = #<match.issue> - Else if
match.planexists and non-empty →target = <match.plan>(use the backlog item's plan field directly) - Else no resolvable target
Execute gate pipeline
If target is resolved:
Skill(skill: "dh:complete-implementation", args: "<target>")
/dh:complete-implementation is the source of truth for the quality-gate phases and final push/PR behavior. Do not duplicate its gate logic here.
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 · 93 lines · 36 tokens per session scan A 6cbd34f85f4e
gate-push is a skill published in the GitHub repository Jamie-BitFlight/claude_skills (66 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 858 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
github
GitHub via gh CLI: PRs, issues, reviews, repos, auth.
github
Full GitHub CLI control — issues, PRs, code reviews, repo management. Uses gh CLI with auth detection, rate limiting, and templates. Triggers on: github, issue, pull request, PR, code review, repo, branch, label, assignee, milestone, release, workflow, actions.
pre-publish-review
Nuclear-grade 12-agent pre-publish release gate. Runs /get-unpublished-changes to detect all changes since last npm release, spawns up to 10 ultrabrain agents for deep per-change analysis, invokes /review-work (orchestrator manual QA plus one gate reviewer) for holistic review, and 1 oracle for overall release…
parallel-pr-review
Use when asked to "review the open PRs", review a batch or stack of pull requests, or run a recurring PR-review pass on a repo — especially with many PRs, stacked branches, conflicts, or security-sensitive changes. Covers grouping, fan-out to review subagents, verdict synthesis, and posting.
oss-maintainer
Run an open-source project's issue/PR/release loop like a careful human maintainer — triage to root cause, absorb community PRs before duplicating them, gate every merge, ship honest releases, and thank the people doing your QA for free.
no-mistakes
Validate committed feature-branch changes through the no-mistakes pipeline: intent, rebase, review, test, docs, lint, push, PR, and CI. Use when the user asks to run no-mistakes, ship safely, validate before pushing, or gate a change before it reaches upstream.