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 companion-inc/introspect --skill tiered-plan-limitsgit clone --depth 1 https://github.com/companion-inc/introspectWrote 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/companion-inc/introspect/tiered-plan-limits)<a href="https://agentmods.dev/skills/companion-inc/introspect/tiered-plan-limits"><img src="https://agentmods.dev/badge/skills/companion-inc/introspect/tiered-plan-limits/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/companion-inc/introspect/tiered-plan-limits"><img src="https://agentmods.dev/badge/skills/companion-inc/introspect/tiered-plan-limits.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 | $0.00111 | $0.01256 |
| Opus 5 | $0.00056 | $0.00628 |
| Sonnet 5 | $0.00022 | $0.00251 |
| Haiku 4.5 | $0.00011 | $0.00126 |
Grade A, and why
tiered-plan-limits 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 10d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tiered plan limits
Problem this handles
When you add a per-tier quantity to a pricing system (a cap, quota, or limit
that differs by plan), the tiers already encode a ratio in their price and
credits. Inventing round numbers (10 / 25 / 100) that look reasonable but
break that ratio is a real, observed failure: shipping maxAutomations at
Plus 10 / Pro 25 / Max 100 drew "did u not see pricing for each plan why is the
multiple off" — because every other field scales 5× then 2×, but 25 is 2.5× of
10. The value was corrected to Pro 50 to restore the ladder.
Activation boundary
Load when: adding or changing a field in PLAN_TIERS or
COMPUTER_RUNTIME_TIERS (src/lib/billing/constants.ts); building a plan gate;
picking a per-plan cap, quota, storage size, rate limit, feature count, or
compute/runtime size (vCPU, RAM, sandbox/E2B template per plan); reviewing such
a change.
Near-misses (do not load): a single non-tiered constant; pricing copy with no quantitative tier ladder; a flat limit that is identical across all plans.
Procedure
- Open
src/lib/billing/constants.tsand readPLAN_TIERS. Add the new limit as a sibling field onPlanTierSpec, in the same source of truth asmonthlyDollars/includedCredits— not a separate parallel constant. - Compute the existing ladder from the fields that already scale with value —
monthlyDollarsandincludedCredits. As of writing: Plus $20 / 2000cr, Pro $100 / 10000cr, Max $200 / 20000cr → Plus→Pro = 5×, Pro→Max = 2×. Re-derive these from the file each time; don't trust this snapshot. - Set the new field to follow that ladder unless there is a stated product reason not to. If the limit should follow a different curve (flat cap, diminishing returns, a hard technical ceiling like Max's storage), say so explicitly and confirm the curve with the user before shipping — do not silently pick round numbers.
- Enforce at the single choke point, mirroring
maxAutomationsForPlan→scheduleTaskForCurrentChat, so both creation paths pass through one gate. - In your report, state the multiple you used (e.g. "5×/2×, matching price and credits") so the user can sanity-check the ratio at a glance.
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.
- 10d ago First seen · 83 lines · 111 tokens per session scan A 74c198651b7e
tiered-plan-limits is a skill published in the GitHub repository companion-inc/introspect (10 stars, last pushed 21d ago), licensed MIT. It adds 111 tokens to every session and 1,256 once invoked, about $0.0006 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
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.