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 agentmods add skills/jayvee/aigon/aigon-research-donpx skills add jayvee/aigon --skill aigon-research-dogit clone --depth 1 https://github.com/jayvee/aigonWrote 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/jayvee/aigon/aigon-research-do)<a href="https://agentmods.dev/skills/jayvee/aigon/aigon-research-do"><img src="https://agentmods.dev/badge/skills/jayvee/aigon/aigon-research-do.svg" alt="Measured on agentmods" 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 | $0.00015 | $0.01387 |
| Opus 5 | $0.00008 | $0.00694 |
| Sonnet 5 | $0.00003 | $0.00277 |
| Haiku 4.5 | $0.00002 | $0.00139 |
Grade A, and why
aigon-research-do 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 6d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
aigon-research-do
Run this command followed by the Research ID.
aigon research-do $ARGUMENTS
Argument Resolution
If no ID is provided, or the ID doesn't match an existing topic in progress:
- List all files in
./docs/specs/research-topics/03-in-progress/matchingresearch-*.md - If a partial ID or name was given, filter to matches
- Present the matching topics and ask the user to choose one
This command is the research equivalent of feature-do: it is the main work step after research-start.
Step 0: Verify your workspace (MANDATORY)
Before doing ANYTHING else, verify your environment:
pwd
git branch --show-current
Research agents work in the main repository on the current branch. This is normal — research does not require branch isolation because you are only writing findings files, not modifying code.
CRITICAL RULES for research:
- You MUST NOT modify any source code files (
.js,.ts,.py,.json, etc.) - You MUST NOT modify other agents' findings files
- You MUST ONLY write to YOUR findings file:
docs/specs/research-topics/logs/research-{ID}-op-findings.md - You MUST NOT run
git checkout,git branch, or create new branches — stay where you are
Required Lifecycle Step
Before starting active research, run:
aigon agent-status implementing
This updates your agent state in the main repo so the dashboard and coordinator know you're actively working.
Your Task
-
Find the research topic in
docs/specs/research-topics/03-in-progress/research-{ID}-*.md -
Check for worktree/Fleet mode: Look for your findings file at:
docs/specs/research-topics/logs/research-{ID}-op-findings.md -
Conduct deep research to answer each question in the research doc. Go broad before going deep:
How to research thoroughly:
- Search the web for documentation, blog posts, comparisons, and real-world usage. Don't rely only on what's in the codebase.
- Read primary sources — official docs, GitHub repos, RFCs — not just summaries.
- Explore multiple approaches before settling on one. For each question, consider at least 2-3 alternatives.
- Look at the codebase to understand current patterns, constraints, and what's already been tried.
- Compare trade-offs with evidence, not just intuition. Include concrete pros/cons.
- Cite your sources — every claim should link back to where you found it.
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.
- 6d ago First seen · 132 lines · 15 tokens per session scan A 4393bb06fde0
aigon-research-do is a skill published in the GitHub repository jayvee/aigon (25 stars, last pushed 5d ago), licensed Apache-2.0. It adds 15 tokens to every session and 1,387 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 2026-08-30.
Other skills, from other repositories
dos-goal-fleet
Launch multiple goal-scoped workers in waves, each with a witness-gated stop condition and dos arbitrate file-tree safety. Use when an operator asks to run several independent goals in parallel and fold only verified ships.
dos-dispatch-loop
Run recurring dos-dispatch cycles, switching to dos-replan when the backlog drains and stopping on the kernel's loop verdict. Use for unattended dispatch->replan->dispatch work across disjoint lanes.
dos-goal-gate
Ground a keep-working goal in evidence the worker did not author by wiring dos hook stop to refuse false done claims. Use for one self-stopping agent or loop worker; use dos-witness-claim for fold barriers.
dos-witness-claim
Route subagent claims through independent read-back before another agent relies on them. Use at parallel, pipeline, or synthesis barriers where shipped phases, files, rows, messages, or other effects must be witnessed.
dos-dispatch
Plan and ship the next batch on one lane: run dos-next-up, acquire a lease with dos arbitrate, gate empty work, dispatch the packet, and archive the run. Use when a single lane should move end to end with collision safety.
dos-enforce-tune
Tune DOS enforcement policy knobs ([interventionpolicy], [intervention], [improve]) from false-deny versus held-catch evidence. Use when running dos enforce-tune to keep only measured nettaskdelta gains and escalate repeated non-keeps.