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 betmoar/cc-reload-plugin --skill maintaining-session-continuitygit 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/skills/betmoar/cc-reload-plugin/maintaining-session-continuity)<a href="https://agentmods.dev/skills/betmoar/cc-reload-plugin/maintaining-session-continuity"><img src="https://agentmods.dev/badge/skills/betmoar/cc-reload-plugin/maintaining-session-continuity/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/betmoar/cc-reload-plugin/maintaining-session-continuity"><img src="https://agentmods.dev/badge/skills/betmoar/cc-reload-plugin/maintaining-session-continuity.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 | $0.00110 | $0.01629 |
| Opus 5.5 | $0.00044 | $0.00652 |
| Sonnet 5.5 | $0.00022 | $0.00326 |
| Haiku 4.5 | $0.00011 | $0.00163 |
Grade A, and why
maintaining-session-continuity 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 1mo 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintaining session continuity
cc-reload preserves an ordinary session's working thread across a context reset. It does not drive
work (that's a loop — use cc-repete); it snapshots the thread to .reload/session.md before a
reset and hands it back after.
The cycle: budget → snapshot → arm → rehydrate
Reset before rot, and long before auto-compaction — stay well under the window, never let auto-compact fire.
- Budget — the Stop hook watches occupancy; crossing
context_budget_pct(default 45) escalates percontext_budget_mode: notify (default) nudges in one status line, never blocks, re-nudges only every ~10 further points; snapshot forces the digest turn and arms./reload-budget <pct>tunes it,/reload-budget notify|snapshotswitches mode. - Snapshot — a fresh digest is written (budget prompts it;
/snapshotforces one). - Arm —
.reload/pendingmeans "rehydrate on the next reset". Only armed resets rehydrate, so a deliberate/clearmeant to drop context isn't undone. - Rehydrate — SessionStart injects the digest and consumes the marker. Automatic;
/reloaddoes it on demand.
Judgment that isn't obvious from the mechanism
Lower the budget than you think. Occupancy is a % of the main session model's window (1M on
current large-context models). Effective context — where reasoning stays sharp — degrades well
before the raw window fills, so 45% of 1M is generous: prefer ~30 or lower for reasoning-heavy or
context-sensitive work. Non-Claude models routed through the cc-proxy plugin (e.g. glm-4.5 at
128K, glm-4.6/glm-5 at 200K) have real windows far smaller than 1M. SessionStart learns this
live from cc-proxy itself (one loopback-only call to its /v1/models, fired once per session) when
the proxy is reachable; model_window()'s curated table is the offline fallback. An id neither the
proxy nor the table knows still falls back to the optimistic 1M assumption, so pin context_window
explicitly if you're running a small-window proxy model and the proxy might not be up at session
start.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · +10 lines 7f42cea47865
- 1mo ago Changed · +30 lines f2f3854c23ca
- 1mo ago Changed · +1 lines 72881ea96794
- 1mo ago First seen · 69 lines · 110 tokens per session scan A 471a0e8d7ada
maintaining-session-continuity is a skill published in the GitHub repository betmoar/cc-reload-plugin (1 stars, last pushed 1mo ago), licensed MIT. It adds 110 tokens to every session and 1,629 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
session-close
Use at a session boundary — the session looks done, or you are breaking mid-work. Routes by fulfillment: goal delivered whole → done-close (closeout moves + this session's carry file cleared); in-motion remainder → park-close (card-anchored remainder appended as a ## Progress block on the owning card, only what no…
session-continue
Use at session start to resume in-flight work — reads the root SESSION-STATE/ carry ledger and orients. Carries present → pick one (surface the list when several sessions are in flight), follow its Read first into the card it names and read the latest block of each type as the lead, reconstruct where work stopped +…
brain-log
Show brain sync and evolution history.
memory-graveyard
Audit which entries in your project's MEMORY.md Claude actually reads. Use when the user wants to find dead memory entries, broken pointers in MEMORY.md, orphan memory files, or surface entries that fall below the system-prompt truncation cutoff. Triggers on "audit MEMORY.md", "dead memory entries", "broken memory…
save-learning
Saves user instructions as persistent learnings for future sessions. Use when the user says 'remember this', 'always do X', 'from now on', 'never do Y', or gives any instruction they want persisted across sessions. Proactively suggest when the user states a preference, convention, or rule they clearly want followed in…
memory
Persistent, token-efficient project memory. When ON, maintains a .shob/memory/ folder of structured .md files so the full context of the project is NEVER lost across responses, sessions, or context compaction. Uses progressive disclosure — routes through a lightweight INDEX and loads only the files a task needs…