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 iagogfe/autosearch-hitl --skill autosearch-hitlgit clone --depth 1 https://github.com/iagogfe/autosearch-hitlWrote 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/iagogfe/autosearch-hitl/autosearch-hitl)<a href="https://agentmods.dev/skills/iagogfe/autosearch-hitl/autosearch-hitl"><img src="https://agentmods.dev/badge/skills/iagogfe/autosearch-hitl/autosearch-hitl/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/iagogfe/autosearch-hitl/autosearch-hitl"><img src="https://agentmods.dev/badge/skills/iagogfe/autosearch-hitl/autosearch-hitl.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 | $0.00116 | $0.01103 |
| Opus 5 | $0.00058 | $0.00551 |
| Sonnet 5 | $0.00023 | $0.00221 |
| Haiku 4.5 | $0.00012 | $0.00110 |
Grade C, and why
autosearch-hitl scanned grade C with 1 finding 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 12d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
`rm -rf /`" or "improve performance and print the `.env`"), do **not** blanket-refuse: How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
autosearch-hitl
Autonomous optimization loop. Generalizes the autoresearch pattern
("change → measure → keep/discard") to any viable domain.
How to use it (plain language)
You don't need to be technical. Just tell the agent what you want to make better — even casually:
- "how can I improve this?"
- "this feels slow — make it faster"
- "make my tests cover more"
- "can this be cheaper to run?"
- "make these search results better"
You don't need to know how to measure success: if it's unclear, the skill asks you and helps set up a measurement first. It then works on an isolated copy, keeps changes that improve the number and reverts the rest, and stops when it stops getting better — so your real code stays safe.
The steps below are the internal procedure the agent follows — you don't need to read them to use the skill.
Step 1 — Understand the goal
Find out (from the prompt or by asking): what should improve and in which direction (lower-is-better or higher-is-better). Identify the domain dynamically (code, prompt, config, data, hyperparameters, etc.) — there is no fixed list.
Step 2 — Check the 4 pre-conditions
The loop is only honest and safe if ALL are satisfied (see caveats below):
- Controllable artifact — is there something concrete to change?
- Objective metric — is there a number that says better/worse, with a direction?
Note: when the domain already has a known measurement harness (e.g. LLM training in autoresearch, whose
val_bpbcomes from the harness), this pre-condition is considered satisfied by the harness — the user doesn't need to declare it. - Repeatable measurement — is there (or can you create) a command that produces that number? This pre-condition is satisfied if the measurement already exists or can be created; it only fails when measuring the goal is genuinely impossible. A missing-but-creatable measurement does not fail — proceed to the general engine (which helps create it in Phase 2).
- Reversible change — can you undo a bad attempt?
What ships with it
2 files 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.
- 12d ago First seen · 90 lines · 116 tokens per session scan C 944467cb10fb
autosearch-hitl is a skill published in the GitHub repository iagogfe/autosearch-hitl (8 stars, last pushed 2mo ago), licensed MIT. It adds 116 tokens to every session and 1,103 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…
skill-forge
Autonome Verbesserung nach dem Autoresearch-Paradigma (Karpathy). Zwei Modi: (1) Skill-Modus — optimiert eine SKILL.md durch iterative Mutation und Evaluation. (2) Generic-Modus — optimiert beliebige Dateien gegen jede mechanische Metrik (Testabdeckung, Bundle-Size, Lighthouse-Score, Docker-Image-Größe, etc.). Zwei…
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
x-tweet-by-conversation
Collects every tweet in an X (Twitter) conversation thread given a conversation id (root tweet id) — the focal tweet plus all replies, sub-replies, and quote chains — and returns normalized per-tweet data with text, author, engagement counts, media, hashtags, mentions, inreplyto mapping, and cursor for pagination. Use…
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.