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/webhook-co/webhook/data-migrationnpx skills add webhook-co/webhook --skill data-migrationgit clone --depth 1 https://github.com/webhook-co/webhookWhat 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 | $0.00043 | $0.00794 |
| Opus 5 | $0.00022 | $0.00397 |
| Sonnet 5 | $0.00009 | $0.00159 |
| Haiku 4.5 | $0.00004 | $0.00079 |
Grade A, and why
data-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 yesterday.
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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data migration
Change the Neon Postgres schema (metadata, config, dedup/idempotency keys) without downtime or data loss. Raw payloads live in R2, not Postgres — migrations touch metadata, not bodies.
Expand → backfill → contract
Never do a breaking change in one step. Split across releases:
- Expand — add new columns/tables (nullable/defaulted), additive only. Deploy. Nothing reads the new shape yet.
- Backfill — populate new fields in idempotent, re-runnable batches, off the hot path. Never hold a long lock on a hot table.
- Contract — switch reads/writes to the new shape, verify, then (in a later release) drop the old shape once rollback is no longer needed.
Safety checklist
- Migration is idempotent and safe to re-run.
- Tenant isolation preserved: RLS policies updated for new/changed tables.
- No PII/PHI moved into logs; no raw payloads pulled into Postgres.
- Tested rollback path exists before production.
- Audit log untouched — never rewrite or delete hash-chained audit history.
- Metering data integrity preserved (event counts stay accurate, single-dimension, dedup-safe).
Applying to prod (schema-before-deploy)
Migrations are applied manually, decoupled from CD, and before the code that depends on them
deploys. Apply with scripts/apply-prod-migrations.sh (with DATABASE_URL set to the prod
webhook_owner connection) — not a bare dbmate up. The script runs the migration and advances
the global prod-schema git tag to the applied commit.
That tag is the deploy migration-guard's source of truth: the three deploy workflows
(deploy.yml / deploy-web.yml / deploy-auth.yml) block an auto deploy whenever HEAD is ahead of
prod-schema by a migration — so new code can never auto-deploy against an un-applied schema. If you apply
with a bare dbmate up, the tag doesn't move and the next migration-bearing push will be blocked with a
message telling you to run the script. Recovery from a block: run the script (applies + advances the tag),
then push — or workflow_dispatch to override (which does not move the tag, so it can't blind the guard).
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.
- yesterday First seen · 61 lines · 43 tokens per session scan A 76047ca84934
data-migration is a skill published in the GitHub repository webhook-co/webhook (0 stars, last pushed 6d ago), licensed Apache-2.0. It adds 43 tokens to every session and 794 once invoked, about $0.0002 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 skills, from other repositories
update-saasmail
Sync the local saasmail repo with the latest upstream changes from https://github.com/choyiny/saasmail. Use this skill whenever the user wants to update saasmail, pull upstream changes, sync with upstream, rebase on upstream, get the latest saasmail, or says "/update-saasmail". Handles adding the upstream remote if…
story-html-publisher
Final step of the AI Storybook pipeline. Consolidates the scenes, images, and per-scene audio into ONE self-contained HTML storybook — a swipe/tap player with every image and audio clip embedded as base64 so the single file works offline and can be shared as-is. Reads {slug}scenes.json, {slug}images.json, and…
github-code-review
Comprehensive GitHub code review with AI-powered swarm coordination.
Pair Programming
AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with…
sparc-methodology
SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration.
Skill Builder
Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization. Use when you need to build custom skills for specific workflows, generate skill templates, or understand the Claude Skills specification.