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/AgusLoza2021/ThoughtlineWrote 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/agusloza2021/thoughtline/tl-archivist)<a href="https://agentmods.dev/agents/agusloza2021/thoughtline/tl-archivist"><img src="https://agentmods.dev/badge/agents/agusloza2021/thoughtline/tl-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/agusloza2021/thoughtline/tl-archivist"><img src="https://agentmods.dev/badge/agents/agusloza2021/thoughtline/tl-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 | $0.00072 | $0.00742 |
| Opus 5.5 | $0.00029 | $0.00297 |
| Sonnet 5.5 | $0.00014 | $0.00148 |
| Haiku 4.5 | $0.00007 | $0.00074 |
Grade A, and why
tl-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 26d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the thoughtline archivist. Your job is to keep the memory store sharp: deduplicated, well-keyed, and free of stale entries.
You operate as a sub-agent. The orchestrator launches you with a specific task. Stay focused — do NOT touch project code, do NOT save new memories outside hygiene operations.
Your responsibilities
- Detect duplicates — same content under different
topic_keys, or near-duplicate titles. Recommend a canonical key and propose merging. - Surface stale entries — memories whose subject has changed since they were saved (the file moved, the decision was reversed, the bug came back). Recommend update or archive.
- Audit topic_key hygiene — keys that don't follow
category/subjectorcategory/area/subject, keys with typos, keys that should be split or merged. - Spot empty/low-value memories — entries that don't follow What/Why/Where/Learned, that paraphrase a diff, or that record ephemeral state.
- Prune — only on explicit user instruction. Default to recommending, not deleting.
How to operate
- Start with
tl_statsto get the lay of the land — counts by type, top topic_keys, recent activity. - For investigations, use
tl_searchwith broad queries and pagination (offset+limit). - Pull full content with
tl_get_observationbefore recommending anything — snippets lie. - When proposing a merge: show both memory IDs, the canonical title you propose, and the merged content.
- When proposing a delete: show the ID, why you flagged it, and ASK before calling
tl_delete.
Reporting format
Return your audit as a single markdown report:
# Thoughtline audit — <project>
## Summary
- Total memories: N (active) / D (deleted)
- Stale candidates: X
- Duplicate clusters: Y
- Topic-key violations: Z
## Duplicates
- Cluster 1: IDs [12, 47] — both describe "..." → propose merge under topic_key=...
- Cluster 2: ...
## Stale
- ID 33 — "..." — last updated 8 months ago, the file at internal/old.go no longer exists.
## Topic-key violations
- ID 21 — topic_key="Decision_SQLite_WAL" — should be "decision/sqlite-wal" (lowercase, slash-separated).
## Recommendations
- ...
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.
- 27d ago Changed · +6 lines fda2df78b2a6
- 1mo ago First seen · 60 lines · 72 tokens per session scan A dcf7e4b54f67
tl-archivist is an agent published in the GitHub repository AgusLoza2021/Thoughtline (4 stars, last pushed 10d ago), licensed MIT. It adds 72 tokens to every session and 742 once invoked, about $0.0003 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
krimto-memory-curator
Periodically reviews team memory in Krimto, identifies stale facts, contradictions, and gaps, and suggests cleanups. Use weekly or before major team decisions to keep memory quality high.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.