A recovery command for applying commits left in a deferred-commit queue to the user's Git branch. It can first show what would be applied.

Use it to inspect or flush queued commits, preserving their order, messages, and original commit identifiers when a fast-forward is possible.

It restores queued work when an automated chain stopped before completing its normal cleanup.

flush — Skill for Claude Code by jeremylongshore

About the project

Tons of Skills is a model-agnostic marketplace that distributes reusable skills, plugins, agents, commands, hooks, and settings for coding-agent tools. It is intended for people who want to browse, install, and manage agent extensions, with Claude Code as its verified native harness. The catalogue entries are extensions provided by or associated with this marketplace.

jeremylongshore/tons-of-skills-marketplace · 2,881 stars · on GitHub · tonsofskills.com

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 jeremylongshore/tons-of-skills-marketplace --skill flush

Clone the repo

git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace

Made for: Claude Code.

Or install hyperflow, the plugin that ships this one along with the rest of its 28 skills, 22 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jeremylongshore/tons-of-skills-marketplace/flush/github.svg)](https://agentmods.dev/skills/jeremylongshore/tons-of-skills-marketplace/flush)

Your own site

<a href="https://agentmods.dev/skills/jeremylongshore/tons-of-skills-marketplace/flush"><img src="https://agentmods.dev/badge/skills/jeremylongshore/tons-of-skills-marketplace/flush/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jeremylongshore/tons-of-skills-marketplace/flush"><img src="https://agentmods.dev/badge/skills/jeremylongshore/tons-of-skills-marketplace/flush.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,157 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.

Model	Per session	Once invoked
Fable 5.1	$0.00097	$0.01157
Opus 5.5	$0.00039	$0.00463
Sonnet 5.5	$0.00019	$0.00231
Haiku 4.5	$0.00010	$0.00116

Measured 1mo ago against content hash 7a2a74cd6a69, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

flush 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.

plugins/ai-agency/hyperflow/skills/flush/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Flush

Manually flush the deferred-commit queue from a chain that ran with commit-when=end. Normally /hyperflow:dispatch calls scripts/flush-commits.sh at its Step 4 wrap-up; this skill exists for the case where the chain was interrupted (crash, kill, context loss) before the auto-flush ran.

Subcommands

Subcommand	Description
(no arg)	Run `scripts/flush-commits.sh <project-root>` — fast-forward staging onto user's branch, delete staging, clear queue
`--dry-run`	Show what would be flushed without doing it. Lists the queued commits in order.

What gets flushed

.hyperflow/commits-queue/manifest.json tracks the chain's user_branch, staging_branch (always hyperflow/staging-<chain-id>), and the list of queued commits with SHAs and messages. Flush replays them via git merge --ff-only so:

All N commits land on the user's branch with original SHAs preserved
Order is chronological (queue-time order)
Original commit messages are preserved
Original file-to-message mapping is preserved (each commit touched exactly the files its sub-task touched)

What happens if fast-forward isn't possible

If the user's branch diverged from staging (e.g. the user committed manually mid-chain on the same branch), git merge --ff-only refuses. The skill surfaces the error with two recovery options:

git rebase hyperflow/staging-<chain-id> — replay staging commits on top of user's new commits
git cherry-pick <staging-base>..hyperflow/staging-<chain-id> — selectively pick commits

The staging branch is preserved for the user to act on manually. The queue manifest stays in place so a future /hyperflow:flush retry can attempt again after the user resolves divergence.

Flow

Check .hyperflow/commits-queue/manifest.json exists. If not, print No queue to flush. and stop.
Run bash $PLUGIN_ROOT/scripts/flush-commits.sh $PROJECT_ROOT [--dry-run].
Print the script's output verbatim.

Overview

/hyperflow:flush is the user-facing handle for the deferred-commit flush mechanism. Most users never call it explicitly — /hyperflow:dispatch Step 4 wrap-up runs the same script automatically. This skill exists for recovery: if a chain ran with commit-when=end and crashed before wrap-up, the queue persists on disk and the user can flush it later.

Read the full file on GitHub · 96 lines

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.

1mo ago First seen · 96 lines · 97 tokens per session scan A 7a2a74cd6a69

Subscribe to this mod's changes

flush is a skill published in the GitHub repository jeremylongshore/tons-of-skills-marketplace (2,881 stars, last pushed today), licensed MIT. It adds 97 tokens to every session and 1,157 once invoked, about $0.0004 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 2026-08-30.

Claude Code DevOps and cloud Git and workflow ai ai-agents automation deferred-commits lifecycle mcp recovery

github-commit-recovery

Recover deleted commits from GitHub using REST API, web interface, and git fetch. Use when you have commit SHAs and need to retrieve actual commit content, diffs, or patches. Includes techniques for accessing "deleted" commits that remain on GitHub servers.

gadievron/raptor · 59 tokens

flush