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 jayvee/aigon --skill aigon-research-spec-reviewgit 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-spec-review)<a href="https://agentmods.dev/skills/jayvee/aigon/aigon-research-spec-review"><img src="https://agentmods.dev/badge/skills/jayvee/aigon/aigon-research-spec-review/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/jayvee/aigon/aigon-research-spec-review"><img src="https://agentmods.dev/badge/skills/jayvee/aigon/aigon-research-spec-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00020 | $0.01409 |
| Opus 5 | $0.00010 | $0.00705 |
| Sonnet 5 | $0.00004 | $0.00282 |
| Haiku 4.5 | $0.00002 | $0.00141 |
Grade A, and why
aigon-research-spec-review 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 10d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
aigon-research-spec-review
Review the research topic spec itself, not the findings. Edit the spec in place using the shared rubric below, then commit the reviewed spec with a spec-review: commit.
Your job: WRITE a review of this research spec. That means reading it, making targeted edits in place, and creating one spec-review: commit that records your findings. You are the reviewer. Do not check for or process anyone else's reviews — that is a separate downstream task (research-spec-revise) and is not what you are doing here.
If git log shows no prior spec-review: commits on this spec, that is expected — your review will be the first. Do not exit with "no pending reviews"; that would be the check workflow, not this one.
You are already inside the spec-review task for this research topic.
- Do not run
aigon research-spec-review $1again. - Do not run
aigon research-spec-revise $1— that is a different command for a later stage, run by the research author after reviewers have completed their review. It is not your job here. - Do not ask the shell to start the same command recursively.
- Use the resolved spec path below, edit that spec in place, then make the required
spec-review:commit and runaigon research-spec-review-record $1. - If you cannot complete the commit or record step, stop and report the blocker instead of making a generic commit.
Resolve the spec
SPEC_PATH=$(find docs/specs/research-topics -maxdepth 2 \( -name "research-$1-*.md" -o -name "research-$1.md" \) | head -1)
test -n "$SPEC_PATH" && echo "$SPEC_PATH"
If SPEC_PATH is empty, stop and report that the research spec could not be resolved.
Read the spec:
cat "$SPEC_PATH"
Review rubric
Spec Review Rubric
Review the spec against this checklist. Prefer small, targeted edits over broad rewrites.
Specificity
- Replace vague language with concrete behavior, constraints, and outcomes.
- Name exact commands, files, states, and data shapes where they matter.
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.
- 10d ago First seen · 141 lines · 20 tokens per session scan A e41a3d7a1bcd
aigon-research-spec-review is a skill published in the GitHub repository jayvee/aigon (25 stars, last pushed 9d ago), licensed Apache-2.0. It adds 20 tokens to every session and 1,409 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
claude-code-expert
Especialista profundo em Claude Code - CLI da Anthropic. Maximiza produtividade com atalhos, hooks, MCPs, configuracoes avancadas, workflows, CLAUDE.md, memoria, sub-agentes, permissoes e integracao com ecossistemas.
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-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-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-self-improve
Run the DOS self-improvement loop: propose a candidate, verify it in an isolated worktree, measure suite/truth/metric gates, and keep only confirmed gains. Use for recursive improvement; use dos-enforce-tune for policy knobs.
dos-supervise-loop
Keep a target count of dispatch loops alive across the workspace lane roster: spawn missing loops, scavenge stalled leases, and surface spinning workers. Use when supervising a DOS dispatch-loop fleet.