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 bradheitmann/odin-sentinel --skill bulk-migrationgit clone --depth 1 https://github.com/bradheitmann/odin-sentinelWrote 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/bradheitmann/odin-sentinel/bulk-migration)<a href="https://agentmods.dev/skills/bradheitmann/odin-sentinel/bulk-migration"><img src="https://agentmods.dev/badge/skills/bradheitmann/odin-sentinel/bulk-migration/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/bradheitmann/odin-sentinel/bulk-migration"><img src="https://agentmods.dev/badge/skills/bradheitmann/odin-sentinel/bulk-migration.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00121 | $0.02286 |
| Opus 5.5 | $0.00048 | $0.00914 |
| Sonnet 5.5 | $0.00024 | $0.00457 |
| Haiku 4.5 | $0.00012 | $0.00229 |
Grade A, and why
bulk-migration 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 2mo 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bulk-migration (odin-scp-integrated)
Runs a verified fleet cascade inside the SCP control plane. It binds the generic bulk-migration
procedure to odin-scp primitives: minimal boot receipts, terminal-locator identity, [SCP-DELEGATE]
receipts, CMUX delivery proof, adversarial QA verdicts, and claim-bound closure.
Companion: the standalone form lives in edge_agentic_orchestration_system/src/skills/bulk-migration/
(self-contained, odin-scp-compatible). That form holds the domain-generality table (software / data /
ML-AI / sysadmin / device-fleet / mobile), the five-object model, the five invariants, the failure-mode
table, and the worked references/control-panel.py dashboard. Read it for the domain model; read THIS
for the SCP bindings. Keep the two synchronized — edit the declared source first, then propagate.
Origin: RFC v2.3 hookchain sync across 18 repos (2026-06-20), run by a droid TEAM-PM + claude DEV + pi QA pod under an A/EXEC-ODIN that was itself a mid-sweep continuation after the first EXEC died.
When to use
Introduce this skill when the operator asks to apply one change across many SCP-governed targets with per-target branch-visible + QA-accepted proof and zero collateral damage — e.g. propagating a governance hook, a config, a migration, or a policy bundle across a repo/host/device fleet.
SCP role bindings
| bulk-migration step | SCP role / artifact |
|---|---|
| Owns the cascade, surface/staffing custody, per-target rotation | A/EXEC-ODIN |
| Owns the roster (operator/Team-A-EXEC modify only) | A/EXEC-PM |
| Routes the per-target pod loop; relays readiness; may NOT self-authorize the commit | TEAM-PM (pod_control) |
| Applies the change with an explicit minimal selector | DEV (implementation) |
| Independent adversarial verify; emits the only valid verdict | QA (quality, read-only) |
| Each seat boots to a role-declaring receipt and holds | SCP boot receipt → BOOTSTRAPPED_IDLE |
| Activation + per-target instructions | [SCP-DELEGATE] |
| Delivery is proven, not assumed | CMUX delivery proof (send + submit + read-back) |
| Closure is branch-visible AND QA-accepted | claim-bound closure |
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.
- 2mo ago First seen · 117 lines · 121 tokens per session scan A 1c6407a5d947
bulk-migration is a skill published in the GitHub repository bradheitmann/odin-sentinel (2 stars, last pushed 10d ago), licensed MIT. It adds 121 tokens to every session and 2,286 once invoked, about $0.0005 per session on Opus 5.5. 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 skills, from other repositories
a2wave-memory
Progressively recall and maintain a2wave cross-session memory through a compact startup catalog, bounded topics, and searchable history.
survey-generator
Compile a structured literature survey on any AI/ML topic. Agent curates a research bundle (taxonomy + sections + bibliography of real papers) from a public anchor resource, then a chosen LLM generates the survey artifact. Output target is a wiki page (markdown), not a one-off HTML — survey lands in /derived/surveys/…
wiki-research-loop
Auto-grow a pro-workflow wiki by running a budget-capped BFS research loop over pluggable source fetchers (web, arXiv, GitHub). Each iteration pops a seed from the queue, fetches sources, drafts a wiki page, dedupes claims against existing pages, enqueues follow-up seeds. Halts on budget cap, depth cap, or…
agent-teams
Coordinate multiple Claude Code sessions as a team — lead + teammates with shared task lists, mailbox messaging, and file-lock claiming. Patterns for team sizing, task decomposition, and when to use teams vs sub-agents vs worktrees.
batch-orchestration
Decompose large-scale changes into independent units and spawn parallel agents in isolated worktrees. Use for migrations, refactors, codemods, and any change touching 10+ files with the same pattern.
design-engineering
Apply interface craft when building or reviewing UI - motion, easing, timing, springs, component feel, and visual foundations. Use when building a component, animation, transition, hover or press state, modal, drawer, toast, or when polishing an interface so it feels right. Says "make this feel better", "add an…