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/yacb2/domaintome/reconcilegit clone --depth 1 https://github.com/yacb2/domaintomeWrote 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/yacb2/domaintome/reconcile)<a href="https://agentmods.dev/commands/yacb2/domaintome/reconcile"><img src="https://agentmods.dev/badge/commands/yacb2/domaintome/reconcile.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 | $0.00024 | $0.00589 |
| Opus 5 | $0.00012 | $0.00295 |
| Sonnet 5 | $0.00005 | $0.00118 |
| Haiku 4.5 | $0.00002 | $0.00059 |
Grade A, and why
reconcile 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run dt reconcile to surface drift between the graph and the current
state of the code. Read-only — never fixes anything automatically. The
user decides what to apply afterwards via targeted dt_update_node
calls.
Steps
-
Determine scope. If
$ARGUMENTScontains a git revision (e.g.HEAD~5,main, a sha), pass it as--since; otherwise do a full scan. -
Run:
dt reconcile --json [--since <rev>]The command exits with code 1 if there is drift, 0 if clean. Either way, parse the JSON from stdout.
-
Summarize in this shape:
## DomainTome reconcile (<scope>) Scanned: N nodes with source_ref. Warnings: <if any, one per line> **dead_refs** (N): source_ref points at a file that no longer exists. - node-id-1 → path:line - node-id-2 → path:line ... **stale** (N): last_verified_at older than <threshold> days. - node-id (last verified D days ago) **never_verified** (N): has source_ref but never marked verified. - node-id Verdict: <one sentence> -
Suggest concrete next actions for each finding:
dead_refs: "Decide per node — either delete (status='archived'), updatesource_refto the new path, or confirm the concept still exists even though the file moved."stale: "Re-verify by inspecting the referenced code, thendt_update_node(id, metadata_patch={'last_verified_at': '<today>'})."never_verified: "After a bootstrap, mark each node verified once you've checked it corresponds to the code."
-
Do not write to the graph. If the user asks for fixes, then write — but each write requires an explicit user decision per node.
Rules
- Never fabricate counts. If reconcile says 0 dead_refs, that is the number. Do not invent findings to look helpful.
never_verifiedis lower priority thanstale. If both lists are large, lead withdead_refsandstale.- If the report includes warnings (e.g. not a git repo), surface them verbatim.
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 · 70 lines · 24 tokens per session scan A 363488f1b151
reconcile is a command published in the GitHub repository yacb2/domaintome (0 stars, last pushed 3mo ago), licensed MIT. It adds 24 tokens to every session and 589 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 2026-08-31.
Other commands, from other repositories
bug-council
Bug Council — spawn 5 diagnostic specialists in parallel to analyze a hard bug from multiple angles, then synthesize a root cause and fix recommendation.
fix
Fix a bug or ship a small change — skip design phase, go straight to sprint planning.
develop-fix
Systematic bug fixing with root cause analysis and regression prevention.
doctor
Health check for greatcto. Shows pipeline state, missing artefacts, hook status, last run per agent, and permission-denied tail.
linkerd
Linkerd-specific diagnostics — mTLS verification, proxy injection issues, authorization policy debugging, traffic management, and multi-cluster connectivity problems.
data-flow-analysis
Trace how data flows through the system from input to output.