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 YSAA1/harness-workflow --skill autoresearchgit clone --depth 1 https://github.com/YSAA1/harness-workflowWrote 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/ysaa1/harness-workflow/autoresearch)<a href="https://agentmods.dev/skills/ysaa1/harness-workflow/autoresearch"><img src="https://agentmods.dev/badge/skills/ysaa1/harness-workflow/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/ysaa1/harness-workflow/autoresearch"><img src="https://agentmods.dev/badge/skills/ysaa1/harness-workflow/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 | $0.00113 | $0.01450 |
| Opus 5.5 | $0.00045 | $0.00580 |
| Sonnet 5.5 | $0.00023 | $0.00290 |
| Haiku 4.5 | $0.00011 | $0.00145 |
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 15d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AutoResearch Research Loop
The user assigns a goal or question — an unknown approach is fine. This skill runs it independently: each round is "research -> hands-on -> review -> distill", checked against the completion criteria; not done yet means another round via the exclusion three questions. One-sentence entry, zero-interruption loop; the difference from deep research is that hands-on work is a first-class citizen — running experiments, writing measurement scripts and changing code to test hypotheses are all normal evidence gathering. Code changes go through implement (an independent experiment subtask that never touches the main research track); ship is never invoked inside a round (closeout is handled uniformly by this skill).
Entry points
autoresearch <goal/question>(materials optional): register the track and start immediately.autoresearch <research-log path>: the goal already sits in the log header; resume directly. On re-entry, search existing logs underdocs/research/first.
Kickoff scan (planner)
- State the need as one deliverable goal (quote the user's verbatim words; any inference beyond them must be marked as such) and start the log (default
docs/research/YYYY-MM-DD--<topic>.md; follow the project's research/notes conventions when present). The header background section = one-sentence goal + scope boundaries + completion criteria + known facts and candidate explanations — fixed for the whole run, guarding against scope swap and drift. The log is the track (self-registered Track header): with a recovery surface,planregisters the row; without one, do not force.harness/; with no lessons surface, distilled entries land in a final section of the log. - Run the scan in parallel: read lessons and existing logs; general web search plus platform channels (when a platform-reading router such as agent-reach is installed, the evidence surface expands automatically — follow that skill's own protocol, e.g. doctor checks; otherwise degrade to general web search + direct primary-source reading). Candidate explanations = the competing hypotheses later rounds must distinguish.
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.
- 15d ago Changed 8c6622d75313
- 1mo ago Changed · -3 lines · +26 tokens per session 156315feec2d
- 1mo ago First seen · 49 lines · 87 tokens per session scan A 616208cc96e7
autoresearch is a skill published in the GitHub repository YSAA1/harness-workflow (3 stars, last pushed 16d ago), licensed MIT. It adds 113 tokens to every session and 1,450 once invoked, about $0.0005 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 2026-09-23.
Other skills, from other repositories
better-harness
Use when /better-harness reviews the outer coding-agent Harness for lifecycle controls, repeated work, project feedback, agent assets, session outcomes, repair planning, durable reports, finding-bound fixes, or manual direct fixes. Invoke only via slash command.
diagnose-backend-bug
Diagnose a bounded backend or multi-service failure from GitHub Issues, Jira, Aone, user-provided exports, logs, traces, responses, stack traces, or job records. Use when a service, API, RPC, worker, queue, CLI, or scheduled job bug needs correlation through the project's existing observability route before repair; do…
intent-correlation-analysis
Analyze a bounded IntentCorrelationPacketV1 and propose reviewable links among user inputs, execution slices, change units, commits, artifacts, and validation outcomes. Use when reconstructing why an observed coding-agent change exists or when Studio needs evidence-backed Intent correlation. Do not use for raw…
generate-harness-dsl
Generate, revise, or review complete Harness as Code .harness files when a coding-agent workflow, agent role, skill, tool contract, MCP connection, runtime, or deployment must be compiler-valid and resolvable with @qoder-ai/harness.
paper-search-usage
This skill should be used when the user asks to "search for papers", "find research papers", "search arXiv", "search PubMed", "look up a DOI", "download a paper", "search IEEE", or "search Scopus".
taxonomy-vto
A reference guide for diagnosing visual problems in LaTeX research papers. It defines categories such as wasted page space, misplaced figures, inconsistent formatting, overflow, alignment, and template-migration issues.