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 smixs/iva-agent --skill update-recoverygit clone --depth 1 https://github.com/smixs/iva-agentWrote 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/smixs/iva-agent/update-recovery)<a href="https://agentmods.dev/skills/smixs/iva-agent/update-recovery"><img src="https://agentmods.dev/badge/skills/smixs/iva-agent/update-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/smixs/iva-agent/update-recovery"><img src="https://agentmods.dev/badge/skills/smixs/iva-agent/update-recovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 20 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 29 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00020 | $0.00922 |
| Opus 5.5 | $0.00008 | $0.00369 |
| Sonnet 5.5 | $0.00004 | $0.00184 |
| Haiku 4.5 | $0.00002 | $0.00092 |
Grade A, and why
update-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 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.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update customization recovery
Iva keeps authored customizations in data/custom/agent/. An update can activate the new core while
placing conflicting base, local and upstream versions in data/update-conflicts/. Resolve those
files here; never apply an old git stash over the whole checkout. A stock-only update can also mean
the custom build or its startup probe failed, without a manifest conflict. An empty conflict list
does not prove the customization was included.
Diagnose before editing
-
Locate this installation: use its
current/directory on an installed Version, or its checkout root on an older installation. Do not diagnose a different checkout or editversions/. -
Follow the read-only commands in docs/troubleshooting.md. Resolve the actual data directory using the shared data-dir helper; do not assume it is
data/. Read the update log locally to distinguish a compile error, failed startup probe, and a held-back version of your files: the last version carrying them did not come up after its restart. Do not infer the cause from the stock notice. In a turn,iva doctoronly checks; repairs belong to the owner's terminal or the Doctor button in/menu.iva diagnoseonly writes a support package. Do not publish raw agent/build logs, custom contents or.envvalues. -
workflow store: 0 runs; 0 hook filesdescribes past workflow runs, not whether customizations are in the build. For two skill sources such asmy-skill.mdandmy-skill/SKILL.md, inspect both locally. The current live resolver prefers the directory package and logs the skipped flat file; a duplicate by itself does not prove why an older build failed. -
Explain the actual error and propose the smallest correction. Before editing or moving any source, preserve both copies outside
custom/agent/andcustom/plugins/so a backup is not another build input. If the copies differ, ask which behavior to keep or offer a semantic merge. Do not automatically delete the flat file, replace all customizations with stock, or clear state.
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.
- 3d ago Changed fbd5b88c35a6
- 13d ago Changed · +1 lines 4cee45d33978
- 19d ago Changed · +38 lines · -2 tokens per session 6fff7216f504
- 1mo ago Changed · -3 lines · -38 tokens per session c1a77bda2f2f
- 1mo ago First seen · 39 lines · 60 tokens per session scan A dcc40ef2b003
update-recovery is a skill published in the GitHub repository smixs/iva-agent (272 stars, last pushed 2d ago), licensed MIT. It adds 20 tokens to every session and 922 once invoked, about $0.0001 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.
Other skills, from other repositories
github-repo-management
Clone, create, fork, configure, and manage GitHub repositories. Manage remotes, secrets, releases, and workflows. Works with gh CLI or falls back to git + GitHub REST API via curl.
github-auth
Set up GitHub authentication for the agent using git (universally available) or the gh CLI. Covers HTTPS tokens, SSH keys, credential helpers, and gh auth — with a detection flow to pick the right method automatically.
updater_guide
Guidance for checking for and installing Row-Bot updates.
developer_pr_prep
Prepare branches, diffs, tests, and GitHub PR text from a conversation's code folder.
pdf-processing
Extract text and tables from PDF files, fill forms, merge documents. Use when working with PDF files or when the user mentions PDFs, forms, or document extraction.
openclaw-github-dedupe
Investigate a cluster of GitHub issues and PRs, determine canonical candidates, post duplicate/related status, preserve contributor credit, and execute cleanup actions. Supports autonomous mode for provided-link-only closeout, merge/fix follow-through, changelog, and post-merge issue/PR cleanup.