reload-budget

reload-budget is a command for Claude Code from betmoar/cc-reload-plugin. It costs 23 tokens per session (536 once invoked), scanned A, original, MIT.

A project command that sets how much of the conversation window can be used before reloading context, and whether to notify you or create a snapshot.

In plain words
What is it for?
Use it to view or change the context percentage and reload behavior for a project.
Why use it?
It helps prevent important conversation details from being lost when the context limit is nearly reached.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the cc-reload plugin — 1 skill, 3 commands, 4 hooks shipped together

Good fit Use it to view or change the context percentage and reload behavior for a project.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add betmoar/cc-reload-plugin
Claude Code
/plugin install cc-reload

Made for: Claude Code.

Or install cc-reload, the plugin that ships this one along with the rest of its 1 skill, 3 commands, 4 hooks.

Wrote 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.

agentmods badge for reload-budget

README.md
[![agentmods](https://agentmods.dev/badge/commands/betmoar/cc-reload-plugin/reload-budget.svg)](https://agentmods.dev/commands/betmoar/cc-reload-plugin/reload-budget)
Your own site
<a href="https://agentmods.dev/commands/betmoar/cc-reload-plugin/reload-budget"><img src="https://agentmods.dev/badge/commands/betmoar/cc-reload-plugin/reload-budget.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 536 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00023 $0.00536
Opus 5 $0.00012 $0.00268
Sonnet 5 $0.00005 $0.00107
Haiku 4.5 $0.00002 $0.00054

Measured 8d ago against content hash e27bf2dbf891, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

reload-budget 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.

commands/reload-budget.md · 37 lines

What it actually says

Set the reload budget

When context crosses the budget, cc-reload either notifies you to run /snapshot + /clear (default — one status line, never interrupts, zero model tokens) or snapshots automatically (snapshot mode: forces a digest-writing turn, then asks you to /clear). Lower the budget for context-sensitive tasks; raise it to get more work per session.

Requested value: $ARGUMENTS

  1. If $ARGUMENTS is empty, report the current settings and stop: bash "${CLAUDE_PLUGIN_ROOT}/scripts/reload-config.sh" get context_budget_pct (empty → default 45) and ... get context_budget_mode (empty → default notify).
  2. If $ARGUMENTS is notify or snapshot (or the legacy checkpoint), set the mode instead of the percentage: bash "${CLAUDE_PLUGIN_ROOT}/scripts/reload-config.sh" set context_budget_mode "$ARGUMENTS".
  3. Otherwise read the old value (same get), then set the new one — do NOT hand-edit the file; the script validates the value, preserves other keys, and creates .reload/ safely: bash "${CLAUDE_PLUGIN_ROOT}/scripts/reload-config.sh" set context_budget_pct "$ARGUMENTS" (accepts 095 or off). If it exits non-zero, relay its stderr message verbatim and stop.
  4. Confirm in one line, e.g. "Reload budget → 30% (was 45%), mode notify — I'll nudge you to /snapshot + /clear when context crosses ~30%."

Note: per-project default. The trigger is best-effort — per-turn token usage from the transcript against the model's window (stamped at session start); if unavailable it falls back to a byte estimate that errs early.

Configuration keys

  • context_owner_window <seconds | off> — how recently another session must have written .reload/session.md for an overwrite to count as a live collision worth side-filing. Default 14400 (4h). off disables the cross-session check entirely.
Changes

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.

  1. 8d ago First seen · 37 lines · 23 tokens per session scan A e27bf2dbf891

Subscribe to this mod's changes

reload-budget is a command published in the GitHub repository betmoar/cc-reload-plugin (1 stars, last pushed 3d ago), licensed MIT. It adds 23 tokens to every session and 536 once invoked, about $0.0001 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.