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 full-stack-skills/agent-skills --skill autoresearchgit clone --depth 1 https://github.com/full-stack-skills/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/full-stack-skills/agent-skills/autoresearch)<a href="https://agentmods.dev/skills/full-stack-skills/agent-skills/autoresearch"><img src="https://agentmods.dev/badge/skills/full-stack-skills/agent-skills/autoresearch/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/full-stack-skills/agent-skills/autoresearch"><img src="https://agentmods.dev/badge/skills/full-stack-skills/agent-skills/autoresearch.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 | $0.00018 | $0.00809 |
| Opus 5 | $0.00009 | $0.00404 |
| Sonnet 5 | $0.00004 | $0.00162 |
| Haiku 4.5 | $0.00002 | $0.00081 |
Grade A, and why
autoresearch 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 8d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autoresearch — Autonomous Goal-directed Iteration
Safety Invariants (all subcommands)
- Never push, publish, or deploy without explicit user approval.
- Bounded by default. Override with
Iterations: unlimited. - All results logged to
autoresearch/{subcommand}-{YYMMDD}-{HHMM}/directory. - Chain handoff via
handoff.json. Evals reads*-results.tsv.
Dispatch (bare $autoresearch)
Parse the invocation in this order:
| Condition | Mode |
|---|---|
Metric: or Verify: present |
Classic — existing metric loop, unchanged |
| Free-form natural-language goal, no metric/verify | Plan — derive a reviewable metric and verification command; do not start an autonomous loop yet |
| Nothing | Setup wizard — interactive config builder |
--classic flag |
Force Classic regardless of goal text |
Print a banner on every invocation: [autoresearch] mode: classic | plan | wizard.
Subcommands
| Command | Does | Default Iterations |
|---|---|---|
$autoresearch |
Iterate against a metric: modify → verify → keep/discard | 25 |
$autoresearch plan |
Convert a goal into validated Scope, Metric, Verify config | N/A |
$autoresearch debug |
Hunt bugs: hypothesize → test → falsify → repeat | 15 |
$autoresearch fix |
Crush errors one-by-one until zero remain | 20 |
$autoresearch security |
STRIDE + OWASP audit with red-team personas | 15 |
$autoresearch ship |
Ship through 8 phases: checklist → dry-run → deploy → verify | N/A |
$autoresearch scenario |
Generate edge cases across 12 dimensions | 20 |
$autoresearch predict |
5 expert personas debate before implementation | N/A |
$autoresearch learn |
Scout codebase → generate docs or wiki → validate → fix loop | 10 |
$autoresearch reason |
Adversarial debate with blind judges until convergence | 8 |
$autoresearch probe |
8 personas interrogate requirements until saturation | 15 |
$autoresearch improve |
Research ICP challenges, discover improvements, generate PRDs | 15 |
$autoresearch evals |
Analyze iteration results: trends, plateaus, regressions | N/A |
$autoresearch regression |
Regression stability gate: baseline vs candidate, verdict STABLE/UNSTABLE | N/A |
What ships with it
20 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.
- agents/openai.yaml 250 B
- autoresearch.md 4.8 KB
- debug.md 4.0 KB
- evals.md 5.0 KB
- fix.md 4.3 KB
- improve.md 6.0 KB
- learn.md 7.9 KB
- LICENSE 1.0 KB
- plan.md 2.8 KB
- predict.md 3.7 KB
- probe.md 4.8 KB
- reason.md 4.7 KB
- references/orchestrator-routing.md 7.2 KB
- references/predict-personas.md 3.1 KB
- references/reason-judge-protocol.md 3.4 KB
- references/security-checklist.md 3.4 KB
- regression.md 9.2 KB
- scenario.md 4.1 KB
- security.md 4.6 KB
- ship.md 4.1 KB
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.
- 8d ago First seen · 65 lines · 18 tokens per session scan A 47220ef2ef29
autoresearch is a skill published in the GitHub repository full-stack-skills/agent-skills (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 18 tokens to every session and 809 once invoked, about $0.0001 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.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.