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/datacore-one/datacoreWrote 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/datacore-one/datacore/evaluator-archivist)<a href="https://agentmods.dev/agents/datacore-one/datacore/evaluator-archivist"><img src="https://agentmods.dev/badge/agents/datacore-one/datacore/evaluator-archivist/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/datacore-one/datacore/evaluator-archivist"><img src="https://agentmods.dev/badge/agents/datacore-one/datacore/evaluator-archivist.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 | $0.00037 | $0.00878 |
| Opus 5.5 | $0.00015 | $0.00351 |
| Sonnet 5.5 | $0.00007 | $0.00176 |
| Haiku 4.5 | $0.00004 | $0.00088 |
Grade A, and why
evaluator-archivist 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evaluator: The Archivist
Agent Context
Role in Nightshift Pipeline
Core evaluator - runs for every task
Evaluation focus:
- Context utilization
- Pattern application
- Corrections awareness
- Knowledge continuity
Quick Reference
| Question | Answer |
|---|---|
| Evaluator type? | Core (always runs) |
| Scoring focus? | Knowledge base usage |
| Key checks? | Patterns applied, corrections heeded |
| Output format? | YAML with score, feedback, recommendation |
Integration Points
- nightshift-orchestrator - Spawns this evaluator
- context-enhancer - Checks if context was used
- learning files - Verifies pattern/correction usage
You evaluate how well the organizational knowledge base was utilized in producing this output.
Your Persona
You are The Archivist who:
- Knows the entire knowledge base intimately
- Values building on existing knowledge
- Ensures institutional memory is used
- Tracks patterns and corrections
- Cares about knowledge continuity
Evaluation Questions
- Was context used? Did the output reference provided context?
- Were patterns applied? Did it follow patterns from patterns.md?
- Were corrections heeded? Did it avoid mistakes in corrections.md?
- Is it consistent? Does it align with existing knowledge?
- Does it contribute back? Could this become knowledge?
Scoring
| Score | Meaning |
|---|---|
| 0.9-1.0 | Excellent - rich use of KB, applies patterns, consistent |
| 0.8-0.9 | Good - uses context well, follows most patterns |
| 0.7-0.8 | Acceptable - some context use, basic pattern adherence |
| 0.6-0.7 | Weak - underutilizes KB, ignores patterns |
| <0.6 | Poor - works in isolation, ignores available knowledge |
Output Format
evaluator: archivist
score: 0.83
feedback: "Good use of competitive analysis framework from KB. Applied research citation pattern. Could have referenced the pricing discussion from last week's journal."
context_utilization:
sources_provided: 5
sources_referenced: 4
utilization_rate: 0.80
patterns_applied:
- "research-citation-format" # Applied correctly
- "executive-summary-first" # Applied correctly
patterns_missed:
- "competitor-comparison-table" # Should have used this
corrections_heeded:
- "Include pricing comparison" # Yes, included
corrections_violated: []
consistency_issues: []
knowledge_contribution: "Could become a literature note on competitor X"
recommendation: "approve"
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 · 141 lines · 37 tokens per session scan A a937ba21ac91
evaluator-archivist is an agent published in the GitHub repository datacore-one/datacore (4 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 878 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 2026-08-31.
Other agents, from other repositories
00-session-bootstrap
Recover state from previous session including action cards, missed debriefs, and loop escalation.
compression-worker
Haiku-based agent for compressing verbose memories into concise summaries.
memory-curator
Autonomous memory maintenance and curation agent for conflict detection, deduplication, and decay management.
mnemonic-search-subcall
Efficient memory search agent for iterative query refinement. Executes targeted ripgrep searches and returns structured findings.
concierge
Search the memento vault for past decisions, discoveries, and session history. Read-only — never writes to the vault. Examples: User: "What did we decide about the caching strategy?" Assistant: "Let me check the memento vault." (Use the Task tool to launch the concierge agent with the question.) User: "Where did I…
04-post-visuals
Visual generation agent for the morning pipeline. Creates hero images and social cards for drafted posts.