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 instructions/betmoar/cc-reload-plugin/claude-mdgit clone --depth 1 https://github.com/betmoar/cc-reload-pluginWrote 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/instructions/betmoar/cc-reload-plugin/claude-md)<a href="https://agentmods.dev/instructions/betmoar/cc-reload-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/betmoar/cc-reload-plugin/claude-md.svg" alt="Measured on agentmods" 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 | $0.10296 | $0.10296 |
| Opus 5 | $0.05148 | $0.05148 |
| Sonnet 5 | $0.02059 | $0.02059 |
| Haiku 4.5 | $0.01030 | $0.01030 |
Grade A, and why
cc-reload-plugin CLAUDE.md scanned grade A with 1 finding 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 today.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
fail-open-silent on literally anything going wrong (down, no `curl`, timeout, bad JSON, missing or How it starts
The opening of the file, as written. The whole thing — 435 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cc-reload — maintainer handoff
This file is the mental model for anyone (human or agent) changing this plugin. Read it before
touching hooks/. The README explains what the plugin does for users; this explains why the
code is shaped the way it is, which invariants are load-bearing, and how to change each piece
without breaking the others.
What this is, in one paragraph
Four bash hooks + three slash commands + one skill that keep a Claude Code session's working
thread alive across context resets. State machine on disk under the user's project at .reload/:
a digest (session.md), a one-shot arm marker (pending, now stamped with its arming session
id when known), a two-pass handshake marker (summarizing), a notify ladder (notified), a
model/window stamp (model), per-project config (config), and — since 0.3 — side-filed digests
from a detected cross-session collision (session.<id>.md). The fourth hook, PreToolUse, is a
same-session enforcement point for that collision guard, not a new continuity mechanism. There is
no daemon, no state anywhere else, and no network on the per-turn hot path — SessionStart makes one
optional loopback-only lookup against a local cc-proxy (see the proxy_window() decision below),
fail-open, never repeated per-turn.
Control flow (the whole system)
Stop hook (every turn end)
├─ summarizing marker present? → PASS 2: consume marker; if digest exists, arm `pending`
│ and VERIFY the arm with -f (not a regular file → "reload NOT armed", never "saved")
│ (fresh digest → success msg; digest not rewritten this turn → arm anyway, warn honestly;
│ no digest → do NOT arm, warn)
│ (occupancy below = the last MAIN-THREAD assistant row of a tail window of the transcript,
│ per-line parsed; full-file stream only if the window holds none — invariant 14)
├─ stop_hook_active && no marker? → stand down (broken handshake must never re-block = loop)
├─ occupancy < budget? → clear the `notified` ladder, exit silently
└─ occupancy ≥ budget → branch on context_budget_mode (default notify):
├─ snapshot mode AND not armed (NO entry at `pending`: -e, not -f — invariant 15) [legacy `checkpoint` aliases here]
│ → PASS 1: write `summarizing` marker and VERIFY it with -f (or refuse to block),
│ emit {decision:"block"} re-injecting "write .reload/session.md, then STOP"
└─ notify mode, OR snapshot mode already armed
→ laddered nudge: {systemMessage} only — never blocks, zero model tokens.
Fires on first crossing, then only at last-notified +10 points (`notified`
stores the %). Ladder unwritable → silent (else it would nag every turn).
PreCompact hook (manual /compact or auto-compaction)
└─ arm `pending`; if no digest exists, write a mechanical fallback stub (honest about being thin)
SessionStart hook (startup|resume|clear|compact)
├─ stamp model id + resolved window to .reload/model (Stop gets no model field — this bridges it)
├─ startup|clear|compact (NOT resume) → purge leaked `summarizing` + `notified`; a handshake
│ must not outlive its context (see invariant 10)
└─ `pending` present? → inject digest as additionalContext + visible systemMessage banner
(WARNS if `pending`'s stamped owner differs from this session's id — never gates on it);
consume the marker (one-shot). Not armed → do nothing (a deliberate /clear is respected).
PreToolUse hook (model Write/Edit)
└─ path == $DIGEST && tool is Write|Edit && payload has session_id?
→ claim-digest.sh: foreign + fresh incumbent -> side-file + warn; ALWAYS exit 0 (permit)
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.
- today Changed · +33 lines · +874 tokens per session de4e8bf54446
- yesterday Changed · +157 lines · +4,209 tokens per session 7beca7b18acf
- 5d ago First seen · 245 lines · 5,213 tokens per session scan A 05e202842025
cc-reload-plugin CLAUDE.md is an instructions file published in the GitHub repository betmoar/cc-reload-plugin (1 stars, last pushed today), licensed MIT. It adds 10,296 tokens to every session, about $0.0515 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
altk-evolve AGENTS.md
AGENTS.md instructions for AgentToolkit/altk-evolve, covering what is evolve?, key concepts, architecture flow, project directory tree (some files omitted for brevity) and first time setup.
agy-plugin-cc CLAUDE.md
Instructions for Vit129/agy-plugin-cc, covering agy-plugin-cc — claude code guide, agent memory, global-first rule, project context (auto-loaded every session) and project summary.
claudemd CLAUDE.md
Claude Code instructions for sdsrss/claudemd, covering code graph (repo-wide ast index) and claude-mem-lite — persistent memory.
ai-handoff AGENTS.md
AGENTS.md instructions for Nazzero/ai-handoff, a project described as: Structured handoff documents for AI coding agents. Type /handoff to generate session summaries for seamless AI-to-AI continuity.
claude-neo4j-mem AGENTS.md
AGENTS.md instructions for troglodyte/claude-neo4j-mem, a project described as: Claude Neo4j memory plugin, in the manner of claude-mem.
aesth CLAUDE.md
Claude Code instructions for zircote-plugins/aesth, covering claude.md, architecture, key concepts, memory-first design and memory types.