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 agentmods add agents/netmindai-open/narranexus/chat_history.pygit clone --depth 1 https://github.com/NetMindAI-Open/NarraNexusWrote 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/netmindai-open/narranexus/chat_history.py)<a href="https://agentmods.dev/agents/netmindai-open/narranexus/chat_history.py"><img src="https://agentmods.dev/badge/agents/netmindai-open/narranexus/chat_history.py.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01419 |
| Opus 5 | $0.00000 | $0.00709 |
| Sonnet 5 | $0.00000 | $0.00284 |
| Haiku 4.5 | $0.00000 | $0.00142 |
Grade A, and why
chat_history.py 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 5d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
2026-07-30 — meta carries the prompt-cache buckets
_build_event_meta's cost_records aggregation now also sums
cache_read_input_tokens / cache_creation_input_tokens into
EventLogMeta.cache_read_tokens / .cache_creation_tokens. Same defect
class as the /costs popover fixed the same day: input_tokens is only the
full-rate bucket, so a cache-warm run's token chip showed "33 in" while
the model actually read ~869k. Buckets stay separate in the API; the
frontend sums for display ([[InnerThoughtCard.tsx]]).
2026-07-23 — event-log meta (activity card header)
get_event_log_detail returns meta: EventLogMeta assembled by
_build_event_meta: env_context.input (capped 4000 chars), lifecycle
(state/started/finished/derived duration — Phase C columns, None on
legacy rows), and a cost_records aggregation by event_id (distinct
models, token sums, total USD — None when no rows so the UI hides the
chip instead of lying with $0). Consumed by [[InnerThoughtCard.tsx]].
Tests: tests/backend/test_event_log_meta.py.
2026-07-10 — clear-history rebuilt as a scoped wipe delegating to wipe_service
DELETE /{agent_id}/history now takes ?conversations=&memory= (default both
true; 400 if neither) and delegates to [[wipe_service.py]]
wipe_agent_data(...). The old inline handler was incomplete — it deleted a
few DB tables but never the on-disk narrative markdown / trajectories (the
real memory; the DB is rebuilt from them on restart) and its session cleanup
globbed the wrong path ({agent}_*.md under the repo dir — the real files are
~/.narranexus/sessions/{agent}_{user}.json), so it deleted nothing. That glob
block is gone. Ownership is now enforced (agents.created_by, 404 for
non-owner) because memory_* is deleted by agent_id — a non-owner wipe would
destroy the owner's memory. ?user_id= is rejected (TDR-12). The
"New-joiner traps" note below is superseded: the full table+disk set now lives
in wipe_service, not this route.
agents/chat_history.py — 聊天历史与对话记录路由
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.
- 5d ago First seen · 82 lines · 0 tokens per session scan A 28d37bc6b9d8
chat_history.py is an agent published in the GitHub repository NetMindAI-Open/NarraNexus (86 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,419 tokens. 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 agents, from other repositories
context-manager
Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…
context
You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.
adapter_grok
Grok is an eagerly registered stock-TUI adapter. RimZ launches grok, installs passive global hooks in ${GROKHOME:-/.grok}/hooks/rimz.json, and enriches each session from its durable updates.jsonl, summary.json, signals.json, and optional events.jsonl files. ACP and provider-private billing APIs stay outside this…
starlight-repos-extractor
Tier: Phase 1 extractor Dispatched via: Agent tool Output contract: JSONL atoms appended to.
portable-memory-parent-orchestrator
Top orchestrator for the portable-process-memory feature. Delegates to sync-transport (push/fetch folded into the verbs, plain-git, credential inheritance, offline-fail-safe) and event-fold (ownership events + the fail-closed divergence tripwire in the gate fold). Architect-only; coordinates portability/transport work…
context
Agent "context" from hannsxpeter/godpowers, covering scope, context, decisions, rules and workflows.