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 Autoloops/greplica --skill greplica-fast-session-bootstrapgit clone --depth 1 https://github.com/Autoloops/greplicaWrote 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/autoloops/greplica/greplica-fast-session-bootstrap)<a href="https://agentmods.dev/skills/autoloops/greplica/greplica-fast-session-bootstrap"><img src="https://agentmods.dev/badge/skills/autoloops/greplica/greplica-fast-session-bootstrap/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/autoloops/greplica/greplica-fast-session-bootstrap"><img src="https://agentmods.dev/badge/skills/autoloops/greplica/greplica-fast-session-bootstrap.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Memory Poisoning · line 62 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
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 | $0.00052 | $0.02201 |
| Opus 5 | $0.00026 | $0.01100 |
| Sonnet 5 | $0.00010 | $0.00440 |
| Haiku 4.5 | $0.00005 | $0.00220 |
Grade A, and why
greplica-fast-session-bootstrap 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 11d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fast Session Bootstrap
Input: a Markdown bundle from:
greplica transcript bundle --platform codex|claude --file <path> [--file <path>...] --out <bundle.md>
Goal: seed useful repo memory from prior sessions. Read the whole bundle, extract every high-signal durable candidate from that bundle, and store focused memories that change what a future agent should do next time. Do not store a broad transcript digest.
Do not store what happened in the session. Store what changes what a future agent should do next time in this repo.
Operating Budget
- Read the whole bundle before choosing what to store.
- Build a candidate inventory across all sessions, not just the first obvious flow.
- Store a complete focused set of durable memories from the bundle. Do not optimize for a fixed memory count.
- Keep each claim narrow and reusable. Split unrelated implementation facts, decisions, constraints, rationale, rejected alternatives, risks, and future work.
- Use
greplica graph contextqueries only to dedupe, reuse existing names, or identify stale memory for bundle-supported candidates. Do not use graph context to discover extra memories that are not in the bundle. - Use targeted code reads sparingly, only when the code surface itself is the durable memory a future agent needs to navigate.
- Leave
supersedes[]empty unless the user explicitly asked to replace stale memory.
Extract Durable Candidates
Build a scratch candidate inventory before writing JSON. Put candidates into these buckets:
- durable repo decisions and constraints;
- component or flow behavior that future agents would otherwise grep to reconstruct;
- non-obvious boundaries, ownership, or similarly named concepts;
- user corrections and gotchas;
- rationale and trade-offs;
- rejected alternatives;
- planned, reverted, or exploratory work that must not be mistaken for implemented behavior;
- explicit future-work boundaries;
- diagnostic/error-message behavior and install-vs-use boundaries;
- evidence/provenance model rules, especially rejected evidence representations;
- accountability gaps where a workflow appears to run but does not clearly mark durable completion;
- environment or installed-binary-vs-checkout gotchas that could mislead future debugging;
- guidance placement and query-shape rules that change how future agents should use Greplica;
- old memory that may need superseding.
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.
- 11d ago First seen · 136 lines · 52 tokens per session scan A 7beb37841225
greplica-fast-session-bootstrap is a skill published in the GitHub repository Autoloops/greplica (433 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 2,201 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
shellm
Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together.