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 commands/techtheist/engram/panegit clone --depth 1 https://github.com/techtheist/engramWhat 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 | $0.00019 | $0.00304 |
| Opus 5 | $0.00010 | $0.00152 |
| Sonnet 5 | $0.00004 | $0.00061 |
| Haiku 4.5 | $0.00002 | $0.00030 |
Grade A, and why
pane 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 2d 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.
What it actually says
Get the Engram graph pane in front of the user.
- If
.engram/daemon.jsonexists in the repo root, read itsportand checkhttp://127.0.0.1:<port>/health. If healthy, the pane is already up — one machine core serves every project (its health reports the home graph; that's normal, the pane's project switcher has this repo). - Otherwise run, from the repository root:
It makes sure the machine core is running (starting it detached if needed), registers this repo with it, prints the pane URL, and exits on its own — no backgrounding needed. Then re-readengram-alpha serve.engram/daemon.jsonfor the real port (the default 8787 may have been taken). - Tell the user the URL (
http://127.0.0.1:<port>) — or, if they use the JetBrains plugin / VS Code extension, that the same pane lives in their IDE's Engram panel.
If the engram-alpha binary is missing, run /engram:setup first instead of improvising an install. If this repo has no .engram/ graph at all, say so — the pane of an unwired repo would be an empty graph.
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.
- 2d ago First seen · 17 lines · 19 tokens per session scan A f19ee342a981
pane is a command published in the GitHub repository techtheist/engram (17 stars, last pushed 2d ago), licensed MIT. It adds 19 tokens to every session and 304 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 2026-08-30.
Other commands, from other repositories
tl-export
Export thoughtline memories to a markdown file the user can review or commit.
tl-search
Search thoughtline memories by keyword or topickey GLOB.
tl-ui
Tell the user how to open the thoughtline TUI dashboard.
tl-recent
Show the most recent thoughtline memories for the active project.
tl-stats
Summarize the thoughtline memory store for the active project.
encode-repo
Bootstrap a repository into Forgetful's knowledge base.