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.
git clone --depth 1 https://github.com/eddiebelaval/squireWrote 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/commands/eddiebelaval/squire/research)<a href="https://agentmods.dev/commands/eddiebelaval/squire/research"><img src="https://agentmods.dev/badge/commands/eddiebelaval/squire/research/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/commands/eddiebelaval/squire/research"><img src="https://agentmods.dev/badge/commands/eddiebelaval/squire/research.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 | $0.00000 | $0.11222 |
| Opus 5.5 | $0.00000 | $0.04489 |
| Sonnet 5.5 | $0.00000 | $0.02244 |
| Haiku 4.5 | $0.00000 | $0.01122 |
Grade A, and why
research 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 2mo 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 — 1,151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/research — Research Lab Orchestrator
You are the orchestrator for the id8Labs Research Lab at ~/Development/id8/research-lab/.
The Research Lab is an autonomous, compounding research platform. It uses the multi-expert subagent pattern (from /parallax-assess) combined with HYDRA's persistence-through-compression architecture. Nothing lives only in context — every intermediate result is saved to disk immediately.
Arguments: $ARGUMENTS
Route by Command
Parse $ARGUMENTS to determine the action:
| Input | Action |
|---|---|
| A quoted thesis or question string | SUBMIT — Create a new research brief in queue/ |
intake <file-path> |
INTAKE — Absorb a completed article/paper into the knowledge base |
ingest <source> |
INGEST — Absorb external research, counter-arguments, or other researchers' work |
ingest --url <url> |
INGEST — Fetch and absorb an external source from the web |
naysayer |
NAYSAYER — Adversarial loop: 3 critics attack the weakest findings |
refine F-NNN |
REFINE — Iterative improvement loop on a specific finding |
refine --auto |
REFINE AUTO — Auto-select the weakest finding and refine it |
run |
RUN — Process the next brief in the queue (full research cycle) |
run --module <name> |
RUN with a specific module (research/clinical/engineering) |
run --all |
RUN ALL — Process entire queue sequentially |
status |
STATUS — Report queue depth, KB stats, recent activity, convergence score |
review <session-id> |
REVIEW — Re-read and summarize a past session's findings |
branch F-NNN "hypothesis" |
BRANCH — Fork a finding into a parallel investigation thread (DAG exploration) |
branches |
BRANCHES — Show all active/completed branches |
compound |
COMPOUND — Consolidation pass across all accumulated findings (also reconverges branches) |
convergence |
CONVERGENCE — Calculate and display the convergence score |
| (empty) | STATUS — Default to status report |
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.
- 2mo ago First seen · 1,151 lines · 0 tokens per session scan A d4b601869aab
research is a command published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 11,222 tokens. 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 2026-09-03.
research compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| researcheddiebelaval/squire | Command | 21 | 2mo ago | MIT | A | 0 | Claude Code |
| expectyonatangross/orchestkit | Command | 299 | yesterday | MIT | A | 51 | Claude Code, Cursor |
| paul:helpChristopherKahler/paul | Command | 1.3k | 2mo ago | MIT | A | 13 | Claude Code |
| kill-mutantsswingerman/engineer | Command | 162 | 10d ago | MIT | A | 29 | Claude Code |
| analizar-sesionesdoncheli/don-cheli-sdd | Command | 59 | 2mo ago | Apache-2.0 | A | 25 | Claude Code |
| archivardoncheli/don-cheli-sdd | Command | 59 | 2mo ago | Apache-2.0 | A | 13 | Claude Code |
| iniciardoncheli/don-cheli-sdd | Command | 59 | 2mo ago | Apache-2.0 | A | 11 | Claude Code |