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 skills/mrobinson2/azureagentforge/honcho-memorynpx skills add mrobinson2/AzureAgentForge --skill honcho-memorygit clone --depth 1 https://github.com/mrobinson2/AzureAgentForgeWrote 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/skills/mrobinson2/azureagentforge/honcho-memory)<a href="https://agentmods.dev/skills/mrobinson2/azureagentforge/honcho-memory"><img src="https://agentmods.dev/badge/skills/mrobinson2/azureagentforge/honcho-memory.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 | $0.00045 | $0.01261 |
| Opus 5 | $0.00023 | $0.00630 |
| Sonnet 5 | $0.00009 | $0.00252 |
| Haiku 4.5 | $0.00005 | $0.00126 |
Grade A, and why
honcho-memory scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Per-step tool output traces, curl commands, etc. — noise, not memory How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Honcho Memory
Query the Honcho persistent memory store via its Dialectic API. Honcho holds long-running facts and observations about peers (users and agents) that have been built up across many conversations.
When to use this skill
- The user asks "what do you know about me?"
- The user asks for personal preferences, habits, history, relationships, or anything specific to them
- You need to recall something the user has previously told an agent
- ANY question where the honest answer requires knowing the user
Do NOT fabricate personal facts from training data or from words present in your system prompt. If pc-honcho returns an empty or unsure answer, say so plainly.
Helper path — resolve dynamically once per session
The helper script lives under the Hermes skills directory but the absolute path varies between containers. Resolve it before use:
HONCHO_HELPER=""
for _p in \
"/paperclip/.hermes/skills/playbooks/honcho-memory/scripts/pc-honcho.sh" \
"/app/skills/playbooks/honcho-memory/scripts/pc-honcho.sh" \
"/opt/data/skills/playbooks/honcho-memory/scripts/pc-honcho.sh"; do
if [ -x "$_p" ]; then HONCHO_HELPER="$_p"; break; fi
done
[ -z "$HONCHO_HELPER" ] && { echo "honcho-memory helper not found"; exit 2; }
Required environment variables (already set on ca-orchestrator)
| Variable | Purpose |
|---|---|
HONCHO_BASE_URL |
Honcho service URL (internal ACA FQDN) |
HONCHO_API_KEY |
Auth token; "self-hosted" in dev |
HONCHO_APP_ID |
Honcho workspace name, e.g. "hermes-dev" |
HONCHO_USER_PEER_ID |
The canonical peer ID for the principal user. Discover with list-peers if unset. |
Subcommands
list-peers
List every peer registered in the workspace. Use this to discover the user's peer ID — it will match whatever ID the upstream channel (e.g. the Telegram bot) uses when writing messages to Honcho.
bash "$HONCHO_HELPER" list-peers
Output is JSON. Look for a peer whose name/id refers to the principal user (e.g. their messaging username or numeric user_id).
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 115 lines · 45 tokens per session scan A 080cc10eb01e
honcho-memory is a skill published in the GitHub repository mrobinson2/AzureAgentForge (21 stars, last pushed 13d ago), licensed MIT. It adds 45 tokens to every session and 1,261 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
mem0-vercel-ai-sdk
Mem0 provider for Vercel AI SDK (@mem0/vercel-ai-provider). TRIGGER when: user mentions "vercel ai sdk", "@mem0/vercel-ai-provider", "createMem0", "retrieveMemories", "addMemories", "getMemories", "searchMemories", "mem0 vercel", "AI SDK provider", "AI SDK memory", or is using generateText/streamText with mem0. Also…
mem0-tour
Browses all stored memories grouped by category with full content display. Use when reviewing all project memories, exploring stored knowledge, onboarding to a project, or getting an overview of captured decisions, conventions, and learnings.
stats
Displays memory usage statistics for the current session and project including counts by category, age distribution, and API latency. Use when checking how many memories exist, reviewing session activity, or auditing memory distribution across categories.
peek
Searches memories and displays compact one-liner results, or looks up a specific memory by ID. Use for quick memory lookups, checking if a decision was recorded, resolving [mem0:id] citations, or browsing memories without full category detail.
pause
Pause Mem0 memory capture on this machine. Use when the user wants to stop memories being recorded, for example for private work or experiments.
mine
Mine a project or conversation into your MemPalace — extract and store memories for later retrieval.