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 RockyHong/super-bootstrap --skill session-continuegit clone --depth 1 https://github.com/RockyHong/super-bootstrapWrote 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/rockyhong/super-bootstrap/session-continue)<a href="https://agentmods.dev/skills/rockyhong/super-bootstrap/session-continue"><img src="https://agentmods.dev/badge/skills/rockyhong/super-bootstrap/session-continue/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/rockyhong/super-bootstrap/session-continue"><img src="https://agentmods.dev/badge/skills/rockyhong/super-bootstrap/session-continue.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 | $0.00156 | $0.01291 |
| Opus 5.5 | $0.00062 | $0.00516 |
| Sonnet 5.5 | $0.00031 | $0.00258 |
| Haiku 4.5 | $0.00016 | $0.00129 |
Grade A, and why
session-continue 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 29d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Continue — Cold-Open Orientation
Mirror of /super-bootstrap:session-close: it lands the carry, this picks it up. The read side of the cold-pickup test — "can a cold session orient from files alone?" — run as a procedure. Consumer of the SESSION-STATE/ ledger — reads every carry in it, claims the one the user picks, leaves the rest as found. Naming, slots, and conflict handling follow session-close's § Ledger convention.
Two entry states
| Detected state | Shape |
|---|---|
Root SESSION-STATE/ holds ≥1 carry, the picked one's pointers resolve |
resume — reconstruct that carry, confirm the next step |
| Folder absent or empty, OR every carry names gone targets | cold-orient — no in-flight carry to take; hand off to /super-bootstrap:needs-me |
Protocol
The gateway runs this inline — it reads the live session's root and docs in its own context, dispatches no subagent, pins no model.
1. Read the ledger
List root SESSION-STATE/ with ls (or Read a concrete path) — an empty glob result is not evidence of absence, so gate on a listing that errors loudly. Any carry file → resume. Folder absent or empty → cold-orient.
Read every carry file. Each is one session's independent carry: an empty or conflict-marked file is dead on its own terms and leaves its siblings fully valid.
A root SESSION-STATE.md left by the single-file contract reads as one more carry — offer it alongside the rest.
2. Resume — pick a carry, then reconstruct
Exactly one live carry → take it. Several → surface the list (label, anchor, next step, last-modified) and let the user pick; the others stay as found. A carry whose owning session is long gone still reads as a normal carry — offer it with its age and let the user resume, leave, or clear it.
Claim the taken carry — rename it <label>-<this-session-id>.md: label kept, id replaced, content untouched. The pick is the gate: a carry nobody took keeps its author's id, and a live session's carry is only claimable when the user — who alone knows what else is running — hands it over.
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.
- 29d ago Changed · +1 tokens per session 5b4ad7fc0db7
- 1mo ago First seen · 64 lines · 155 tokens per session scan A 7cbb94475b86
session-continue is a skill published in the GitHub repository RockyHong/super-bootstrap (3 stars, last pushed 5d ago), licensed MIT. It adds 156 tokens to every session and 1,291 once invoked, about $0.0006 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 2026-09-28.
Other skills, from other repositories
session-handoff
Create consistent session handoff documents for context transfer between sessions. Use when closing a session, reaching 75% token consumption, or when user requests handoff. Ensures proper YAML headers for metrics collection, LF line endings, and complete documentation of progress, decisions, and next steps.
brain-log
Show brain sync and evolution history.
maintaining-session-continuity
Judgment for using cc-reload — carrying a session's working thread across a context reset via .reload/session.md: snapshot, arm, rehydrate after /clear, /compact, or auto-compaction. Use when saving state before a reset, handing off mid-task, holding working state as context fills, or working with /snapshot, /reload…
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…
principle-guard-the-context-window
Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not raw payloads.
compound-docs
Searchable Elixir/Phoenix/Ecto solution documentation system with YAML frontmatter. Builds institutional knowledge from solved problems. Use when consulting past solutions before investigating new issues.