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 davidtoby/agent-skills --skill github-auth-recoverygit clone --depth 1 https://github.com/davidtoby/agent-skillsWrote 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/davidtoby/agent-skills/github-auth-recovery)<a href="https://agentmods.dev/skills/davidtoby/agent-skills/github-auth-recovery"><img src="https://agentmods.dev/badge/skills/davidtoby/agent-skills/github-auth-recovery/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/davidtoby/agent-skills/github-auth-recovery"><img src="https://agentmods.dev/badge/skills/davidtoby/agent-skills/github-auth-recovery.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 | $0.00090 | $0.00780 |
| Opus 5.5 | $0.00036 | $0.00312 |
| Sonnet 5.5 | $0.00018 | $0.00156 |
| Haiku 4.5 | $0.00009 | $0.00078 |
Grade A, and why
github-auth-recovery 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.
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Auth Recovery
Diagnose GitHub auth failures before retrying commands blindly.
Quick start
- Inspect the remote URL and current branch.
- Check whether
ghis authenticated. - Test whether GitHub SSH already works.
- If SSH works, prefer SSH over broken HTTPS credential flows.
- Fetch/rebase before pushing if the remote branch may have advanced.
- Verify the remote commit after push.
Core workflow
1. Inspect the repo state
Run:
git remote -v
git branch --show-current
git status --short
Identify whether origin is using HTTPS or SSH.
2. Check gh separately from git
Run:
gh auth status
Important: gh being unauthenticated does not imply GitHub SSH is unavailable.
3. Check HTTPS failure mode
If the remote is HTTPS and push/pull fails, capture the actual error first.
Typical signal:
fatal: could not read Username for 'https://github.com': Device not configured
This usually means the current HTTPS credential path is unusable in the current environment.
4. Test SSH before doing anything more complex
Run:
ssh -T [email protected]
If you get a success message like:
Hi <user>! You've successfully authenticated...
then prefer SSH git operations instead of continuing to fight HTTPS.
5. Switch strategy, not just credentials
If SSH works:
- use SSH for
git push - you may keep
originunchanged and push directly to an SSH URL, or update the remote if appropriate
Example direct push:
git push [email protected]:owner/repo.git HEAD:main
6. Re-sync with remote before push
Do this when someone else—or another process—may have updated the remote branch while you were debugging auth.
git fetch origin main
git rebase origin/main
Do not assume auth was the only problem. A stale local base can make the next push fail even after auth is fixed.
7. Verify the outcome
After push:
- inspect local HEAD
- confirm the remote commit SHA or latest commit message
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.
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 · 129 lines · 90 tokens per session scan A 78d6f12b87ab
github-auth-recovery is a skill published in the GitHub repository davidtoby/agent-skills (11 stars, last pushed 2mo ago), licensed MIT. It adds 90 tokens to every session and 780 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 2026-09-03.
Other skills, from other repositories
commit
Skill "commit" from clacky-ai/openclacky, covering smart commit skill, critical requirement: single-line commits only, core philosophy, usage and process steps.
devops-pipeline
Configure pre-commit hooks and lean GitHub Actions for shift-left quality assurance. Use when adding or auditing CI/CD to maximize local test coverage and minimize CI cost. Skip for Terraform/K8s, deployment pipelines, or non-GitHub CI providers.
auto-push
Generate a commit message, stage all changes, and push to remote after scanning for secrets, large files, and protected-branch risks. Skip for opening PRs, code review, or cutting releases/tags.
commit
Create commit messages following Sentry conventions. Use when committing code changes, writing commit messages, or formatting git history. Follows conventional commits with Sentry-specific issue references.
create-pr
Create pull requests following Sentry conventions. Use when opening PRs, writing PR descriptions, or preparing changes for review. Follows Sentry's code review guidelines.
codex-review
Professional code review with auto CHANGELOG generation, integrated with Codex AI.