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 commands/with-geun/alive-analysis/analysis-wikigit clone --depth 1 https://github.com/with-geun/alive-analysisWrote 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/with-geun/alive-analysis/analysis-wiki)<a href="https://agentmods.dev/commands/with-geun/alive-analysis/analysis-wiki"><img src="https://agentmods.dev/badge/commands/with-geun/alive-analysis/analysis-wiki.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 | $0.00000 | $0.01887 |
| Opus 5 | $0.00000 | $0.00944 |
| Sonnet 5 | $0.00000 | $0.00377 |
| Haiku 4.5 | $0.00000 | $0.00189 |
Grade A, and why
analysis-wiki 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 4d 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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/analysis-wiki
Maintain the Analysis Wiki — a structured, AI-maintained knowledge base built from your team's analyses.
Subcommands: update | check | show {entity}
Instructions
Step 1: Parse subcommand
Read $ARGUMENTS:
updateor no argument → rebuild wiki from analyses (go to Step 2a)check→ health-check the wiki for issues (go to Step 2b)show {entity}→ display a wiki page (go to Step 2c)
Step 2a: Update
Goal: Scan all analyses and compile/update structured wiki pages.
Step 2a-1: Inventory
Read:
.analysis/config.md— team context, metrics list, languageanalyses/decisions/INDEX.md— existing DRs (to link wiki pages to decisions)
List all archived analyses:
analyses/archive/— all folders recursively/analysis-wiki updatealways does a full scan (not incremental) to ensure wiki accuracy. For large archives, this takes longer but prevents stale pages from persisting.
If analyses/wiki/ doesn't exist yet, create the directory structure:
analyses/wiki/
├── INDEX.md
├── metrics/
│ └── INDEX.md
├── patterns/
│ └── INDEX.md
└── hypotheses/
└── INDEX.md
Step 2a-2: Extract from each analysis
For each archived analysis, read:
summary.md— key findings, type, tags01_ask.md— primary metric, hypothesis tree03_investigate.md— hypothesis scorecard results, statistical findings05_evolve.md— proposed new metrics, follow-up analyses
Extract:
- Metrics referenced: note the metric name + how it was defined in this analysis
- Hypotheses tested: each hypothesis from the scorecard + its result (validated / rejected / inconclusive) + effect size
- Key findings: top 1-2 VOICE-stage findings for this metric
- Patterns detected: look for notes about Simpson's paradox, seasonality, sampling bias, etc.
Step 2a-3: Build/update metric pages
For each unique metric found across analyses:
If analyses/wiki/metrics/{metric-slug}.md already exists:
- Append new findings to the Key Findings section
- Add new hypothesis results to the appropriate section (Validated / Rejected / Inconclusive)
- Update Watch Points if new quirks found
- Update
Last updatedandSource analysescount
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.
- 4d ago First seen · 220 lines · 0 tokens per session scan A 2eda003374fe
analysis-wiki is a command published in the GitHub repository with-geun/alive-analysis (41 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,887 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 2026-08-30.
Other commands, from other repositories
save-session-learnings
Document session learnings to CLAUDE.md and AGENTS.md. Use after completing significant tasks, debugging sessions, or discovering project patterns.
kiro-steering-custom
Command "kiro-steering-custom" from gotalab/cc-sdd, covering kiro custom steering creation, workflow, available templates, steering principles and tool guidance.
memory-why
Show why a memory recall returned what it did -- BM25 vs vector vs hybrid provenance.
wiki-synthesize
Synthesize wiki/sources/ .md pages from raw session transcripts using the configured LLM backend.
review-code
Read ALL memory bank code rules + best practices, check the files that changed, and APPLY fixes so they adhere. The active counterpart to /scan (which is read-only). Use after an AI session, before commit, to make changed files compliant.
lians-recall
Recall current (non-stale) facts from Lians memory, optionally as-of a past date.