go-on

go-on is a skill for Claude Code, Codex from auerbachb/claude-code-config. It costs 81 tokens per session (10,545 once invoked), scanned A, original, MIT.

A work-resumption helper for coding-agent sessions that were paused, ended, interrupted, or stalled. It examines the recorded stop state and chooses a resume path.

In plain words
What is it for?
Resuming interrupted coding, review, pull-request, and merge workflows, including sessions ended by crashes, sign-outs, or token limits.
Why use it?
It helps continue unfinished work without guessing what happened or which step is safe to repeat.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/auerbachb/claude-code-config/go-on
Any agent
npx skills add auerbachb/claude-code-config --skill go-on
Clone the repo
git clone --depth 1 https://github.com/auerbachb/claude-code-config

Made for: Claude Code, Codex.

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.

agentmods badge for go-on

README.md
[![agentmods](https://agentmods.dev/badge/skills/auerbachb/claude-code-config/go-on.svg)](https://agentmods.dev/skills/auerbachb/claude-code-config/go-on)
Your own site
<a href="https://agentmods.dev/skills/auerbachb/claude-code-config/go-on"><img src="https://agentmods.dev/badge/skills/auerbachb/claude-code-config/go-on.svg" alt="Measured on agentmods" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 10,545 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00081 $0.10545
Opus 5 $0.00041 $0.05273
Sonnet 5 $0.00016 $0.02109
Haiku 4.5 $0.00008 $0.01055

Measured 3d ago against content hash 55ab61ad54fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

go-on 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 3d 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.

.claude/skills/go-on/SKILL.md · 605 lines

How it starts

The opening of the file, as written. The whole thing — 605 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Resume the work, whatever stopped it. Step 0 classifies the stoppage from recorded evidence and routes; Steps 0b–10 are the interrupted-review-workflow lane it routes to.

Portable helper resolution (workflow lane)

Resolve every lifecycle helper before entering Steps 0b–10, not before Step 0: classification needs only the stop-state helpers resolved in 0.2, and a resume that just routes to /pause-resume must not be blocked by a missing merge-gate helper it will never call. Inside the workflow lane a missing helper blocks rather than guessing which completed state is safe.

resolve_script() {
  local name="$1" candidate
  for candidate in \
    "$HOME/.claude/skills-worktree/.claude/scripts/$name" \
    "$HOME/.claude/scripts/$name" \
    ".claude/scripts/$name"; do
    if [[ -x "$candidate" ]]; then echo "$candidate"; return 0; fi
  done
  return 1
}
PR_AUTHORSHIP_SH=$(resolve_script pr-authorship.sh || true)
DIFF_SURVIVAL_SH=$(resolve_script diff-survival-check.sh || true)
REVIEWER_OF_SH=$(resolve_script reviewer-of.sh || true)
PR_STATE_SH=$(resolve_script pr-state.sh || true)
REPLY_THREAD_SH=$(resolve_script reply-thread.sh || true)
RESOLVE_REVIEW_THREADS_SH=$(resolve_script resolve-review-threads.sh || true)
MERGE_GATE_SH=$(resolve_script merge-gate.sh || true)
AC_CHECKBOXES_SH=$(resolve_script ac-checkboxes.sh || true)
[[ -n "$PR_AUTHORSHIP_SH" ]] || { echo "ERROR: pr-authorship.sh not found (checked all three paths) — resume authorship gate unavailable" >&2; exit 1; }
[[ -n "$DIFF_SURVIVAL_SH" ]] || { echo "ERROR: diff-survival-check.sh not found (checked all three paths) — rebase survival gate unavailable" >&2; exit 1; }
[[ -n "$REVIEWER_OF_SH" ]] || { echo "ERROR: reviewer-of.sh not found (checked all three paths) — reviewer routing unavailable" >&2; exit 1; }
[[ -n "$PR_STATE_SH" ]] || { echo "ERROR: pr-state.sh not found (checked all three paths) — PR state unavailable" >&2; exit 1; }
[[ -n "$REPLY_THREAD_SH" ]] || { echo "ERROR: reply-thread.sh not found (checked all three paths) — review replies unavailable" >&2; exit 1; }
[[ -n "$RESOLVE_REVIEW_THREADS_SH" ]] || { echo "ERROR: resolve-review-threads.sh not found (checked all three paths) — thread resolution unavailable" >&2; exit 1; }
[[ -n "$MERGE_GATE_SH" ]] || { echo "ERROR: merge-gate.sh not found (checked all three paths) — merge gate unavailable" >&2; exit 1; }
[[ -n "$AC_CHECKBOXES_SH" ]] || { echo "ERROR: ac-checkboxes.sh not found (checked all three paths) — acceptance verification unavailable" >&2; exit 1; }

Walk through the full review lifecycle checklist in order. At each step, check if it's already been completed. Stop at the first incomplete step and execute it, then continue to the next step. Keep going until the workflow is complete or a blocking condition is hit.

Output a status line at each step so the user can follow along:

  • [DONE] — step already completed, moving on
  • [ACTION] — step incomplete, executing now
  • [BLOCKED] — step cannot proceed, reporting why
  • [SKIP] — step not applicable

Read the full file on GitHub · 605 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.

  1. 3d ago First seen · 605 lines · 81 tokens per session scan A 55ab61ad54fc

Subscribe to this mod's changes

go-on is a skill published in the GitHub repository auerbachb/claude-code-config (5 stars, last pushed 4d ago), licensed MIT. It adds 81 tokens to every session and 10,545 once invoked, about $0.0004 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 2026-08-31.