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/florianbruniaux/claude-code-plugins/stage-2-researchnpx skills add FlorianBruniaux/claude-code-plugins --skill stage-2-researchgit clone --depth 1 https://github.com/FlorianBruniaux/claude-code-pluginsWrote 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/florianbruniaux/claude-code-plugins/stage-2-research)<a href="https://agentmods.dev/skills/florianbruniaux/claude-code-plugins/stage-2-research"><img src="https://agentmods.dev/badge/skills/florianbruniaux/claude-code-plugins/stage-2-research.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 | $0.00068 | $0.01501 |
| Opus 5 | $0.00034 | $0.00750 |
| Sonnet 5 | $0.00014 | $0.00300 |
| Haiku 4.5 | $0.00007 | $0.00150 |
Grade A, and why
talk-stage2-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 5d 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Talk Stage 2: Research (REX mode only)
Builds the git proof for a REX talk. Cross-references git history, CHANGELOG, and the Stage 1 summary to produce a verified timeline and velocity analysis.
Automatically skipped in --concept mode. Only runs when the source material is a REX with git repository access.
When to Use This Skill
- After Stage 1 (Extract) when building a REX talk
- When you have access to the project's git repository
- To verify metrics mentioned in the source material against actual git data
What This Skill Does
- Reads the summary: understands the period and themes from Stage 1
- Git archaeology: extracts velocity metrics (read-only commands only)
- Changelog analysis: scans releases, features, documented metrics
- Cross-references: aligns git, CHANGELOG, and summary
- Builds the timeline: verified dates, not estimated
- Writes 3 output files
Input
talks/{YYYY}-{slug}-summary.md(from Stage 1, required)repo_path: absolute path to the git repository- Optional: CHANGELOG path if different from
{repo_path}/CHANGELOG.md
Output
Three files:
talks/{YYYY}-{slug}-git-archaeology.mdtalks/{YYYY}-{slug}-changelog-analysis.mdtalks/{YYYY}-{slug}-timeline.md
Git Commands (read-only only)
# Commits by month
git -C {repo_path} log --pretty=format:"%Y-%m" | sort | uniq -c
# Commits by contributor
git -C {repo_path} shortlog -sn --no-merges
# First and last date
git -C {repo_path} log --pretty=format:"%ad" --date=short | tail -1
git -C {repo_path} log --pretty=format:"%ad" --date=short | head -1
# Merged PRs (if merge commit convention)
git -C {repo_path} log --merges --oneline | wc -l
# Tags (releases)
git -C {repo_path} tag --sort=version:refname
# Velocity peak (busiest months)
git -C {repo_path} log --pretty=format:"%Y-%m" | sort | uniq -c | sort -rn | head -5
Output Formats
git-archaeology.md
# Git Archaeology: {slug}
**Repo**: {repo_path}
**Period analyzed**: {start date} -> {end date}
**Commands run**: {list}
## Global Metrics
| Metric | Value | Source |
|--------|-------|--------|
| Total commits | {n} | git log |
| Total merges/PRs | ~{n} | git log --merges |
| Total releases (tags) | {n} | git tag |
| Human contributors | {n} | git shortlog |
| Period covered | {n} months | first -> last date |
## Monthly Velocity
| Month | Commits | Notes |
|-------|---------|-------|
| {YYYY-MM} | {n} | {context if notable} |
...
## Contributors
| Rank | Name | Commits | % |
|------|------|---------|---|
| 1 | {name} | {n} | {%} |
...
---
*Generated by talk-stage2-research: {date}*
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.
- 5d ago First seen · 194 lines · 68 tokens per session scan A 4884357daeb3
talk-stage2-research is a skill published in the GitHub repository FlorianBruniaux/claude-code-plugins (40 stars, last pushed 3d ago), licensed MIT. It adds 68 tokens to every session and 1,501 once invoked, about $0.0003 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
vc-autopilot
Emit and validate the provisional goal block for Autopilot Mode. Owns the 9-field format and resume detection from a pasted goal block.
vc-problem-solving
Apply systematic problem-solving techniques when stuck. Use for complexity spirals, innovation blocks, recurring patterns, assumption constraints, simplification cascades, scale uncertainty.
thoroughness-scoring
Score every decision point with a Thoroughness Rating (1-10). AI makes the marginal cost of doing things properly near-zero — pick the higher-rated option every time. Includes scope checks to distinguish contained vs unbounded work.
report
Read the delivery log and say which rules actually fire, which never have, and what to prune or fix. Use when the user asks whether ballast is doing anything, wants to clean up their rule catalog, or on a periodic review.
orchestrate
Wire Commands, Agents, and Skills together for complex features. Use when building features that need research, planning, and implementation phases.
squid-self-improve
Analyze developer corrections from the current coding session and persist lessons learned as rules in AGENTS.md files or memory. Use at the end of a session after the developer corrected your work, when they say "squid-self-improve", ask to capture what was learned, or ask you to reflect on mistakes and extract…