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 iampawan/Manifest --skill critic-scalabilitygit clone --depth 1 https://github.com/iampawan/ManifestWrote 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/iampawan/manifest/critic-scalability)<a href="https://agentmods.dev/skills/iampawan/manifest/critic-scalability"><img src="https://agentmods.dev/badge/skills/iampawan/manifest/critic-scalability/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/iampawan/manifest/critic-scalability"><img src="https://agentmods.dev/badge/skills/iampawan/manifest/critic-scalability.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 | $0.00036 | $0.00574 |
| Opus 5 | $0.00018 | $0.00287 |
| Sonnet 5 | $0.00007 | $0.00115 |
| Haiku 4.5 | $0.00004 | $0.00057 |
Grade A, and why
critic-scalability 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 9d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scalability critic
Protocol: Follow
reference/CRITIC-RULES.md(the compact runtime rules) at the plugin root for severity definitions (the closed enum blocker/warning/info), the output JSON schema, ID prefixes, and shared anti-patterns. This skill defines only WHAT to look for. Do not invent severities like "high"/"medium" — the validator rejects them. Do not re-check anything the deterministic validator (scripts/validate.mjs) already covers; add the judgment layer on top.
You read for things that work fine at 100 users and break at 100K.
What to check
1. Query patterns
For each data-touching behavior:
- Is the access pattern point lookups, range scans, or full scans?
- Are there obvious N+1 risks (loop with per-item fetches)?
- Are indexes implied by the access pattern?
2. Unbounded growth
- Is there a list / collection that grows over time? (notifications, comments, history, sessions)
- Is pagination, archival, or cap policy specified?
- For event-sourced flows: is there a snapshot or compaction strategy?
3. Hot paths
- Is this behavior invoked on a hot user surface (every page load, every API call)?
- If yes: cache strategy spec'd? TTL? invalidation rules?
4. Concurrent writes
- Does the behavior mutate shared state?
- Conflict resolution: last-write-wins, optimistic locking, CRDT, queue?
- Idempotency: can the same request be retried safely?
5. External dependencies
- Does the behavior call out to a third-party in a synchronous user flow?
- Timeout / retry strategy?
- Circuit breaker?
- What happens when the third-party is degraded vs down?
6. Background work
- If a behavior triggers async work, is the queue/worker named?
- Retry policy?
- Dead-letter handling?
- Are there expected throughput bounds?
7. Cost surface
- Does the behavior trigger expensive operations (LLM calls, image generation, large transcoding)?
- Cost per invocation? Cap per user / org?
- Cost alerting?
Severity
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.
- 9d ago First seen · 77 lines · 36 tokens per session scan A 8e85975f6a1c
critic-scalability is a skill published in the GitHub repository iampawan/Manifest (5 stars, last pushed 6d ago), licensed MIT. It adds 36 tokens to every session and 574 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
platform-apex-generate
Primary Apex authoring skill for class generation, refactoring, and review. ALWAYS ACTIVATE when the user mentions Apex, .cls, triggers, or asks to create/refactor a class (service, selector, domain, batch, queueable, schedulable, invocable, DTO, utility, interface, abstract, exception, REST resource). Use this skill…
flow-next-impl-review
Carmack-level implementation review of changes via the configured backend. Use when asked to review code or a diff in a flow-next repo.
flow-next-resolve-pr
Resolve PR review feedback. Fetches unresolved threads, triages, fixes, replies and resolves via GraphQL. Use when asked to address review comments.
api-contract-review
Use when auditing CloudBase cloud API wrappers, MCP tools, generated action metadata, or related docs for outdated or incorrect action names, parameters, casing, request shapes, or missing contract tests, especially during periodic quality review or before preparing corrective PRs.
api-reviewer
A review of an API contract, the agreed description of how software systems exchange requests, responses, events, or files.
principle-model-the-domain
Apply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files. Encode the domain in a structure instead of scattered conditionals.