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 Ahmad-Jaradat-Space/co-scientist-plugin --skill running-research-sessionsgit clone --depth 1 https://github.com/Ahmad-Jaradat-Space/co-scientist-pluginWrote 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/ahmad-jaradat-space/co-scientist-plugin/running-research-sessions)<a href="https://agentmods.dev/skills/ahmad-jaradat-space/co-scientist-plugin/running-research-sessions"><img src="https://agentmods.dev/badge/skills/ahmad-jaradat-space/co-scientist-plugin/running-research-sessions/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/ahmad-jaradat-space/co-scientist-plugin/running-research-sessions"><img src="https://agentmods.dev/badge/skills/ahmad-jaradat-space/co-scientist-plugin/running-research-sessions.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 | $0.00088 | $0.01893 |
| Opus 5 | $0.00044 | $0.00946 |
| Sonnet 5 | $0.00018 | $0.00379 |
| Haiku 4.5 | $0.00009 | $0.00189 |
Grade B, and why
running-research-sessions scanned grade B 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 11d 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
signed-in CLI by itself, so never tell the user to set an API key unless they How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Running research sessions
The engine takes a research goal and runs Generation, Reflection, an Elo tournament, Evolution and Meta-review until a termination criterion fires. It holds all state in SQLite. Your job is to frame the goal well, agree how large the run should be, launch it, and report progress honestly.
A session runs for minutes to hours and makes hundreds of model calls. Never start one without an explicit go-ahead on that size.
What the usd numbers mean
The usual setup is the Claude Code or Codex CLI the user is already signed
into. There is no API key and nothing is charged. doctor and
estimate_cost both report billing, which is subscription in that case and
metered when a real API key is paying.
Some engine fields are still named budget_usd and budget_used_usd, because
the engine was built against a metered API. Under subscription they are a
token odometer, not a price: the engine counts tokens, multiplies by
published rates, and stops when the counter reaches the cap. Report them as
usage against the user's plan, never as money, and never imply a bill. What you
ask a go-ahead for is scale: how many model calls, and how much wall clock.
Workflow
Copy this checklist and tick as you go:
- [ ] 1. Check the install (doctor)
- [ ] 2. Sharpen the research goal with the user
- [ ] 3. Show the size of the run and get a go-ahead
- [ ] 4. Start the session
- [ ] 5. Poll until it finalises
- [ ] 6. Hand over the overview
1. Check the install
Call co-scientist:doctor. If backend_ready is false, stop and report
backend_detail. Nothing downstream works without a backend.
If backend_ready is false on a fresh install, the fix is almost always that
the CLI is not signed in (claude, or codex login). The server picks up a
signed-in CLI by itself, so never tell the user to set an API key unless they
have deliberately chosen a metered backend.
embeddings will report the local hash embedder. That is the expected state
for a keyless install: dedup catches literal overlap only, so near-duplicate
hypotheses may both survive and pairings are less informative. Say it once, as
a caveat on the results, not as something to fix.
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.
- 11d ago First seen · 173 lines · 88 tokens per session scan B a42bd183c4c3
running-research-sessions is a skill published in the GitHub repository Ahmad-Jaradat-Space/co-scientist-plugin (0 stars, last pushed 23d ago), licensed Apache-2.0. It adds 88 tokens to every session and 1,893 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
glycoengineering
Analyze and engineer protein glycosylation. Scan sequences for canonical N-glycosylation sequons (N-X-S/T with X not proline, including overlapping sites), predict O-GalNAc hotspots, read glycan notation, and reach the curated external tooling (NetNGlyc, NetOGlyc, GlycoShield, GlycoWorkbench, GlyTouCan, GlyConnect).…
molecular-dynamics
Run and analyze molecular dynamics simulations with OpenMM and MDAnalysis. Set up protein and protein-ligand systems with PDBFixer, choose force fields and water models (AMBER14, CHARMM36m, ff19SB, GAFF2, TIP3P), solvate and add ions, run energy minimization, NVT/NPT equilibration and production MD on GPU, then…
molfeat
Molecular featurization hub with one consistent interface over 100+ featurizers. Fingerprints (ECFP/Morgan, MACCS, atom pair, topological torsion, Avalon, RDKit, ERG), RDKit and Mordred descriptor sets, pharmacophore and 3D shape descriptors, scaffold keys, and pretrained embeddings (ChemBERTa, ChemGPT, MolT5, GIN…
depmap
Query the Cancer Dependency Map (DepMap) for cancer cell line gene dependency scores (CRISPR Chronos), RNAi DEMETER2 scores, PRISM compound sensitivity, and gene effect profiles across the cell-line panel. Use for identifying cancer-selective vulnerabilities, separating pan-essential genes from selective ones, finding…
pytdc
Use Therapeutics Data Commons through the PyTDC Python package for registry discovery, approved dataset access, task-aware splits (scaffold, cold-start, temporal, combination), evaluator metrics, benchmark groups, and bounded molecular-oracle workflows. Use this skill to find which TDC datasets exist for a therapeutic…
rowan
Rowan is a cloud-native molecular modeling and medicinal-chemistry workflow platform with a Python API. Use for pKa and macropKa prediction, conformer and tautomer ensembles, docking and analogue docking, protein-ligand cofolding, MSA generation, molecular dynamics, permeability, descriptor workflows, and related…