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/docxology/template/agents-memory-updatergit clone --depth 1 https://github.com/docxology/templateWrote 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/docxology/template/agents-memory-updater)<a href="https://agentmods.dev/agents/docxology/template/agents-memory-updater"><img src="https://agentmods.dev/badge/agents/docxology/template/agents-memory-updater.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 | $0.00039 | $0.00559 |
| Opus 5 | $0.00019 | $0.00280 |
| Sonnet 5 | $0.00008 | $0.00112 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
agents-memory-updater 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.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local agent memory updater
Own the full memory update flow for continual learning in this public template repo.
Trigger
Use from continual-learning when transcript deltas may produce durable memory updates.
Target files
- Memory (read/write):
.cursor/hooks/state/continual-learning-memory.json - Schema (read-only):
.cursor/hooks/state/continual-learning-memory.example.json - Index (read/write):
.cursor/hooks/state/continual-learning-index.json
Optional deterministic merge via:
uv run python -c "from pathlib import Path; from infrastructure.core.agent_memory import load_memory, save_memory, normalize_bullets; ..."
Workflow
- Read existing memory JSON first. If missing, copy structure from the example file (version 1, empty arrays).
- Load the incremental index if present.
- Inspect only transcript files under
~/.cursor/projects/<workspace-slug>/agent-transcripts/that are new or have newer mtimes than the index. - Pull out only durable, reusable items:
- recurring user preferences or corrections
- stable workspace facts
- Update memory JSON carefully:
- update matching bullets in place (same topic → revise existing string)
- add only net-new bullets
- deduplicate semantically similar bullets
- cap each array to at most 12 bullets (
learned_user_preferences,learned_workspace_facts) - set
updated_atto current ISO-8601 UTC timestamp
- Refresh the incremental index for processed transcripts; remove entries for files that no longer exist.
- If the merge produces no memory changes, leave memory unchanged but still refresh the index when transcripts were scanned.
- If no meaningful updates exist, respond exactly:
No high-signal memory updates.
Guardrails
- Plain bullet strings in JSON arrays only — no evidence/confidence tags, no nested metadata.
- Do not write secrets, private credentials, one-off instructions, or transient session details.
- Never edit root
AGENTS.mdLearned sections (enforced bytest_root_agents_is_public_repo_contract_not_personal_memory). - Exclude paths, API keys, and machine-local home directories unless they are stable workspace conventions already documented in public docs.
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.
- 3d ago First seen · 56 lines · 39 tokens per session scan A 34db7a278207
agents-memory-updater is an agent published in the GitHub repository docxology/template (19 stars, last pushed today), licensed Apache-2.0. It adds 39 tokens to every session and 559 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
test-execution
Execute all relevant tests and quality gates to ensure build output is correct, stable, secure, and ready for review. This is feature-flow's Phase 3 (and Phase 3.5 for live-system verification) — local, pre-push verification. Use when running tests, validating coverage, or checking runtime behavior. Distinct from the…
test
Writes failing tests before implementation, increases coverage on existing code, and generates language-appropriate test patterns. Use when implementing TDD, fixing a coverage gap, or adding tests for a new feature.
measure
Monthly DORA metrics agent. Scheduled trigger (not human-prompted). Queries uFawkesObs for delivery metrics, computes ROI snapshot, flags anomalies for the learn agent, feeds improvement items to the plan agent.
discover
Pre-spec user research agent. Run before any spec session begins. Produces a discovery brief that anchors the spec, design, and acceptance test agents to real user needs.
verifier
Skeptical, read-only validator. Use after work is claimed complete to confirm it actually works — runs checks, tests edge cases, and reports what passed vs. what is incomplete or broken.
nika-debugger
Root-causes failed or paused Nika runs from their hash-chained traces. Use when nika run exited red, a run paused on a prompt and needs the exact resume line, a NIKA-XXXX runtime finding needs a cause, or a trace must be verified and explained. Evidence-first — reads .nika/traces via nika trace; its craft is the…