solve-issue

solve-issue is a skill for Codex from sago-cream/human-out-of-loop. It costs 53 tokens per session (614 once invoked), scanned A, original, MIT.

A workflow that selects eligible GitHub issues, implements fixes in isolated workspaces, and publishes the changes through pull requests.

In plain words
What is it for?
It is for solving one exact issue or dispatching work on multiple open issues that are not already covered by pull requests.
Why use it?
It removes repetitive issue selection and setup when several independent fixes need to be made, while keeping each change separate.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Codex; $skill-name invocation.

Good fit It is for solving one exact issue or dispatching work on multiple open issues that are not already covered by pull requests.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sago-cream/human-out-of-loop/solve-issue
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 sago-cream/human-out-of-loop --skill solve-issue
Clone the repo
git clone --depth 1 https://github.com/sago-cream/human-out-of-loop

Made for: 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 solve-issue

README.md
[![agentmods](https://agentmods.dev/badge/skills/sago-cream/human-out-of-loop/solve-issue/github.svg)](https://agentmods.dev/skills/sago-cream/human-out-of-loop/solve-issue)
Your own site
<a href="https://agentmods.dev/skills/sago-cream/human-out-of-loop/solve-issue"><img src="https://agentmods.dev/badge/skills/sago-cream/human-out-of-loop/solve-issue/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.

agentmods 80×15 button for solve-issue

Your own site · 80×15
<a href="https://agentmods.dev/skills/sago-cream/human-out-of-loop/solve-issue"><img src="https://agentmods.dev/badge/skills/sago-cream/human-out-of-loop/solve-issue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 614 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.
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 5.1 $0.00053 $0.00614
Opus 5 $0.00026 $0.00307
Sonnet 5 $0.00011 $0.00123
Haiku 4.5 $0.00005 $0.00061

Measured 11d ago against content hash dea13e05f67b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

solve-issue 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 11d 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.

skills/solve-issue/SKILL.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Select

  • $solve-issue #<positive-issue-number>: solve that issue in the current task; never create a worker or substitute another issue.
  • $solve-issue <positive-amount>: select that many distinct eligible issues in ascending order and immediately create one sidebar-visible task per issue in parallel. If fewer qualify, dispatch all remaining eligible issues and report the shortage.
  • $solve-issue: solve one eligible issue in the current task.

Eligible: open, with no open or draft PR covering it through a GitHub Development link or closing keyword. Ignore incidental mentions. Recheck once before dispatch.

Exact-target failure:

ISSUE_SKIPPED issue=<number> reason=<not_found|not_open>
ISSUE_SKIPPED issue=<number> reason=covered_by_pr pr=<url>

Dispatch

  • Keep exact and default runs in the invoking task. For amount runs, use only the selected issue tasks; do not create separate developer, reviewer, or publication tasks.
  • Give every issue an isolated worktree and branch named <type>/<short-kebab-description>, using the narrowest of fix, feat, docs, refactor, test, or chore. Never namespace it.
  • Call set_thread_title once per task and never change it:
    • Exact/default task: Solve #<issue>
    • Amount orchestrator: Solve <amount> issues
    • Amount worker: #<issue>: <short-description>
  • Give each amount worker the repository, issue + URL, base, branch, absolute worktree, and optional media path. The orchestrator only dispatches, waits, reports terminal results, and resumes existing workers without duplicating them.

Solve

Each issue-owning task completes the whole workflow:

  1. Activate $ponytail at full intensity.
  2. Implement the issue, run relevant checks, and commit the complete solution.
  3. For UI changes, keep .codex-pr-media/ untracked through .git/info/exclude and capture matched, reproducible before/after media: video for interaction, motion, or multiple steps; images otherwise.
  4. Require a clean worktree except ignored PR media, then run $pr.
  5. If $pr finds actionable problems, fix and commit them, rerun checks, and invoke $pr again. Repeat in the same task until it publishes a draft PR.
  6. Report the issue, published head, PR URL, and checks. Never merge or mark a PR ready.

Read the full file on GitHub · 43 lines

Files

What ships with it

1 file 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.

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. 11d ago First seen · 43 lines · 53 tokens per session scan A dea13e05f67b

Subscribe to this mod's changes

solve-issue is a skill published in the GitHub repository sago-cream/human-out-of-loop (6 stars, last pushed 22d ago), licensed MIT. It adds 53 tokens to every session and 614 once invoked, about $0.0003 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.

Related

Other skills, from other repositories