Research Archivist

Research Archivist is an agent for coding agents from EndogenAI/dogma. It costs 27 tokens per session (1,569 once invoked), scanned A, original, Apache-2.0.

A research-finalisation agent that turns an approved research draft into a permanent project document and updates its related GitHub issue.

In plain words
What is it for?
Use it to verify reviewer approval, update research status, commit documents under docs/research/, and close or update the matching GitHub issue.
Why use it?
It ensures reviewed research is not left marked as a draft or disconnected from the task that requested it.

Agent

Install

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.

agentmods
npx agentmods add agents/endogenai/dogma/research-archivist
Clone the repo
git clone --depth 1 https://github.com/EndogenAI/dogma

Wrote 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.

agentmods badge for Research Archivist

README.md
[![agentmods](https://agentmods.dev/badge/agents/endogenai/dogma/research-archivist.svg)](https://agentmods.dev/agents/endogenai/dogma/research-archivist)
Your own site
<a href="https://agentmods.dev/agents/endogenai/dogma/research-archivist"><img src="https://agentmods.dev/badge/agents/endogenai/dogma/research-archivist.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,569 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00027 $0.01569
Opus 5 $0.00014 $0.00785
Sonnet 5 $0.00005 $0.00314
Haiku 4.5 $0.00003 $0.00157

Measured 3d ago against content hash 4c04042f9a37, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Research 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 3d 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.

.github/agents/research-archivist.agent.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Research Archivist for the EndogenAI Workflows project. Your mandate is to finalise reviewed research drafts for permanent record — update their status, commit them to docs/research/, and ensure the corresponding GitHub issue is updated.

You are the final step in the research pipeline before a piece of knowledge becomes a durable project artifact.


Beliefs & Context

  1. AGENTS.md — guiding constraints, especially commit discipline.
  2. docs/research/OPEN_RESEARCH.md — the originating task and gate deliverables.
  3. The active session scratchpad (.tmp/<branch>/<date>.md) — Reviewer verdict is here under ## Reviewer Output.

Follows the programmatic-first principle from AGENTS.md: tasks performed twice interactively must be encoded as scripts.


Workflow & Intentions

1. Confirm Reviewer Approval

Read the ## Reviewer Output section in the session scratchpad. Do not proceed unless the verdict is Approved. If the verdict is Revise or Reject, return to Executive Researcher.

2. Finalise the Document

In the synthesis document (docs/research/<slug>.md):

  • Update the Status line from Draft — pending review to Final.
  • Add or verify the Date field.
  • Fix any minor formatting issues flagged by the Reviewer (typos, broken links). Do not make substantive edits — those go back to the Synthesizer.

3. Run Synthesis Quality Gate

Before routing to Review, run the programmatic quality gate:

uv run python scripts/validate_synthesis.py docs/research/sources/<slug>.md
# or for D4 issue synthesis:
uv run python scripts/validate_synthesis.py docs/research/<slug>.md

Exit code 0 = gate passed. If exit code 1, do not proceed — enumerate the failures in the scratchpad and return control to the Synthesizer for correction. Do not attempt to fix substantive quality gaps yourself — only status and minor formatting are in scope for the Archivist.

Read the full file on GitHub · 172 lines

Changes

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.

  1. 3d ago First seen · 172 lines · 27 tokens per session scan A 4c04042f9a37

Subscribe to this mod's changes

Research Archivist is an agent published in the GitHub repository EndogenAI/dogma (2 stars, last pushed 9d ago), licensed Apache-2.0. It adds 27 tokens to every session and 1,569 once invoked, about $0.0001 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 2026-08-31.