Borrowing it
Nothing to install: this file belongs to Pseudogiant-xr/Pseudolife-MCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Pseudogiant-xr/Pseudolife-MCP/master/.claude/skills/schema-bump/SKILL.mdgit clone --depth 1 https://github.com/Pseudogiant-xr/Pseudolife-MCPWrote 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/pseudogiant-xr/pseudolife-mcp/schema-bump)<a href="https://agentmods.dev/skills/pseudogiant-xr/pseudolife-mcp/schema-bump"><img src="https://agentmods.dev/badge/skills/pseudogiant-xr/pseudolife-mcp/schema-bump/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/pseudogiant-xr/pseudolife-mcp/schema-bump"><img src="https://agentmods.dev/badge/skills/pseudogiant-xr/pseudolife-mcp/schema-bump.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 | $0.00065 | $0.01058 |
| Opus 5.5 | $0.00026 | $0.00423 |
| Sonnet 5.5 | $0.00013 | $0.00212 |
| Haiku 4.5 | $0.00006 | $0.00106 |
Grade A, and why
schema-bump 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 8d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Schema change and schema bump checklist
A schema bump touches several files that each have a guard test, and the Rust port pins the schema in more places still. Missing one fails CI in a lane the master ruleset does not require, so it is easy to merge broken. The v30 bump found steps 7 and 8 the hard way; the v56 bump missed every Rust step below and four Parity jobs failed, and its CLI harness goldens failed a second round after the first re-record.
A. Every schema bump (Python side, all in one PR)
- The version.
SCHEMA_META_VERSIONinpseudolife_memory/storage/schema.py. - The docs. The README capabilities table, and in
docs/guide/configuration.mdthe DSN row and the version-history table.tests/test_release_ux.pypins both, the history table including gap detection. - The version pin. The single
CURRENT_SCHEMAliteral intests/test_schema_version.py. No per-version test file and no>=relaxation pass: the ladder is gap-checked bytest_release_ux.pyandtest_atlas_currency.py. - The behaviour's test. Whatever the bump adds gets a test beside its
consumer, or a row in
tests/test_schema_ddl_shape.pyif it is pure DDL shape. Never a newtest_schema_vNN.py. - The changelog. A
vNNmention in the change'schangelog.d/fragment (test_release_ux.pyreads CHANGELOG.md plus pending fragments). - The atlas.
docs/atlas/atlas.jsonmeta.schema, pinned bytests/test_atlas_currency.py. Re-verify the affected storage cards; don't just renumber. - The embedding-migration pins. The two
assert meta[0] == NNliterals intests/test_migrate_embeddings.py. - The generated docs.
python ops/gen_llms_txt.pyafter any doc edit (tests/test_llms_txt.pypins the generatedllms-full.txt).
B. Any change to schema.py, bump or not
The Rust plan hashes the whole file, so even a comment change needs this.
- Regenerate the Rust daemon's embedded schema plan:
python rust/daemon/harness/gen_schema_sql.py, then the same command with--checkmust pass. The changedschema.sql,schema_plan.jsonandschema_meta.rsunderrust/daemon/src/storage/ship in the same PR. - When the DDL or migrations change, re-record the schema startup
golden
rust/daemon/harness/goldens/schema-startup.json:python rust/daemon/harness/schema_ci.py --record-goldens --out <scratch>/schema-record.json. It needs the bench Postgres, a Rust toolchain, and the commits listed inrust/daemon/harness/schema_history.json;--no-build --rust-test-bin <exe>reuses a built test binary. Inspect the golden's diff, then run it again without--record-goldensto check.
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.
- 8d ago First seen · 79 lines · 65 tokens per session scan A ec1dfb304256
schema-bump is a skill published in the GitHub repository Pseudogiant-xr/Pseudolife-MCP (6 stars, last pushed today), licensed Apache-2.0. It adds 65 tokens to every session and 1,058 once invoked, about $0.0003 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 2026-10-20.
Other skills, from other repositories
adk-redis
Redis backends for Google's Agent Development Kit (ADK). Use this skill when the user wants to back an ADK agent with Redis: persistent sessions and long-term memory via Redis Agent Memory Server, RAG search tools over a RedisVL index (vector / hybrid / range / text / SQL), MCP toolsets for RedisVL or Agent Memory…
another-brain
Use the another-brain MCP tools (remember, search, recent, get, reinforce, forget) as shared long-term memory. Activates at the start of a task that may continue previous work, when recalling past decisions/fixes/preferences, when learning something worth remembering across sessions or agents, or after using a…
lore-onboard
First-time setup wizard for LoreConvo. Verifies the MCP server is connected, the database is accessible, hooks are configured, and runs a test save/load cycle. Use when the user says "set up loreconvo", "onboard", "/lore-onboard", "verify loreconvo", "test loreconvo setup", or after first installing the plugin.
agent-memory-discipline
Rules for when an agent should recall from long-term memory before acting and when it should save decisions, corrections and failures afterwards. Works with any memory backend.
dev-browser
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website"…
memanto-companion
Inspect and manage the cross-session engineering memory that Memanto maintains for your Claude Code skills. Use when the user asks what Memanto remembers, wants to see their engineering profile, manually recall context for a skill, or store a decision. The automatic lifecycle hooks handle capture/injection on their…