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/techtheist/engramWrote 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/commands/techtheist/engram/setup)<a href="https://agentmods.dev/commands/techtheist/engram/setup"><img src="https://agentmods.dev/badge/commands/techtheist/engram/setup/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/commands/techtheist/engram/setup"><img src="https://agentmods.dev/badge/commands/techtheist/engram/setup.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 | $0.00028 | $0.00481 |
| Opus 5.5 | $0.00011 | $0.00192 |
| Sonnet 5.5 | $0.00006 | $0.00096 |
| Haiku 4.5 | $0.00003 | $0.00048 |
Grade C, and why
setup scanned grade C with 2 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 21d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/techtheist/engram/main/install.sh | sh -s -- --bin-only Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/techtheist/engram/main/install.sh | sh -s -- --bin-only What it actually says
Wire the current repository to Engram. The plugin already provides the capture skill, the session-brief hook and the MCP server globally — the server only binds repositories that are wired, so the per-repo work is the binary and marking this repo as a project. Never install a project-level skill, hook, or .mcp.json entry here.
-
Binary. Check
command -v engram-alpha(also~/.local/bin/engram-alphaand~/.cargo/bin/engram-alpha). If missing, ask the user once for consent to install, then run:curl -fsSL https://raw.githubusercontent.com/techtheist/engram/main/install.sh | sh -s -- --bin-onlyIf they decline, stop and point them at https://github.com/techtheist/engram#install. If
engram-alpha --versionis older than 0.9.9, runengram-alpha update— the plugin's server needsmcp --wired-only. -
Wire the repo. From the repository root:
engram-alpha setup --cli claude --mcp-onlyThis git-ignores
.engram/and creates it — the directory is what tells the plugin's server this repo is a project. With the plugin installed it writes no.mcp.jsonentry (that would load every engram tool twice); if it reports an existingengramentry in.mcp.json, remove that entry. -
Connect. Tell the user to run
/mcpand reconnect theengramserver (or start a new session) so it binds this repo. The next session opens pre-briefed via the plugin's SessionStart hook. -
Cold start. If this created a brand-new graph, mention that once connected, the skill offers a one-time seeding pass from the project's existing docs/history — and that
/engram:paneopens the graph UI.
If anything fails, report the exact error — never pretend the repo is wired.
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.
- 21d ago Changed · +4 tokens per session af050534f3df
- 1mo ago Changed 96ac40bbfe1e
- 1mo ago First seen · 25 lines · 24 tokens per session scan C 34651abab0da
setup is a command published in the GitHub repository techtheist/engram (32 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 481 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
status
Show memex statistics and status including projects, memos, and pending items.
open
Open the memex vault in Finder or Obsidian.
tl-export
Export thoughtline memories to a markdown file the user can review or commit.
tl-ui
Tell the user how to open the thoughtline TUI dashboard.
log
Command "log" from allenc84/sapience, covering /log — judgment ledger command, routing, new assessment: /log, review: /log review [domain] and resolve: /log resolve.
crew-activate
Activate an expert persona (CEO, CFO, CMO, CTO, PM, Analyst, Creative, Support).