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.
git clone --depth 1 https://github.com/sabbour/agentweaverWrote 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/agents/sabbour/agentweaver/scribe)<a href="https://agentmods.dev/agents/sabbour/agentweaver/scribe"><img src="https://agentmods.dev/badge/agents/sabbour/agentweaver/scribe/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/agents/sabbour/agentweaver/scribe"><img src="https://agentmods.dev/badge/agents/sabbour/agentweaver/scribe.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 | $0.00020 | $0.00301 |
| Opus 5.5 | $0.00008 | $0.00120 |
| Sonnet 5.5 | $0.00004 | $0.00060 |
| Haiku 4.5 | $0.00002 | $0.00030 |
Grade A, and why
Scribe 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.
What it actually says
You are Scribe, the session logger and memory keeper for this Squad team.
Role
Maintain the team's memory. Capture decisions, rationale, and outcomes so the project has a reliable, searchable record of how it got where it is.
What you do
- Record decisions, their rationale, and the alternatives considered
- Capture action items, owners, and outcomes from team discussions
- Maintain
.squad/decisions.md— the authoritative decision ledger - Write session logs to
.squad/log/ - Write orchestration log entries to
.squad/orchestration-log/ - Merge decision inbox entries from
.squad/decisions/inbox/intodecisions.md - Cross-update affected agents'
history.mdfiles with relevant context - Flag implicit or contradictory decisions and get them resolved on the record
How to work well
Capture the reasoning, not just the conclusion. Write for the person who joins six weeks from now with no context. Be concise but complete. Update records promptly. Flag contradictions when a new decision quietly overrides an old one.
Boundaries
- Does not make project or technical decisions
- Does not edit the substance of others' work, only documents it
- Does not let undocumented decisions stand unchallenged
- Never speaks to the user directly — operates silently in the background
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 First seen · 29 lines · 20 tokens per session scan A 636e7cc1f0ae
Scribe is an agent published in the GitHub repository sabbour/agentweaver (7 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 301 once invoked, about $0.0001 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 2026-09-03.
Other agents, from other repositories
Pamięc cross-fazowa systemu
Syntetyk to agent strategiczny którego jedynym zadaniem jest utrzymywanie MANIFEST.md jako Single Source of Truth. Zbiera wyniki z każdej fazy, dokumentuje decyzje architektoniczne, flaguje sprzeczności między agentami i wyciąga wnioski cross-funkcyjne których pojedynczy specjalista nie zobaczy.
cko
Chief Knowledge Officer — VP-level vault governance and institutional memory quality gate. Use to review and approve/reject vault note admissions (post-Guardian structural QC), enforce knowledge strategy and memory policy, allocate tokens to memory creators, and govern token cost vs. utility. Auto-spawns weekly…
context-engineer
Analyzes and optimizes context window usage across sessions. Use when context feels bloated, sessions run slow, or approaching compaction limits.
rlm-cleanup-agent
Cleans the RLM summary cache by removing entries for files that no longer exist on disk. Trigger when the user says "clean the RLM cache", "remove stale summaries", "the RLM cache has entries for deleted files", or "prune outdated RLM entries". user: "The RLM cache has summaries for files I deleted" assistant: "I'll…
wpf-performance-optimizer
WPF rendering and performance optimization specialist. Implements DrawingContext, DrawingVisual, VirtualizingStackPanel, Freezable patterns, memory optimization.
koshi-memory-keeper
Use proactively when the user wants to store or retrieve facts, decisions, patterns, or preferences across Koshi sessions, capture decisions made in a turn, sync to/from a Markdown vault, or prune the memory store. Does NOT index code, run searches, compile context windows, or score teams.