letta-ai/letta-code is an agent harness for building assistants that retain memory, identity, and experience across interactions instead of treating each task as isolated. Developers use it through local, desktop, browser, or messaging interfaces for interactive or continuously running agents, and its catalogue entries configure the agents' skills, instructions, rules, and behavior.
Borrowing it
Nothing to install: this file belongs to letta-ai/letta-code. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/letta-ai/letta-code/main/.skills/capturing-tui-visual-proof/SKILL.mdgit clone --depth 1 https://github.com/letta-ai/letta-codeWrote 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/letta-ai/letta-code/capturing-tui-visual-proof)<a href="https://agentmods.dev/skills/letta-ai/letta-code/capturing-tui-visual-proof"><img src="https://agentmods.dev/badge/skills/letta-ai/letta-code/capturing-tui-visual-proof/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/skills/letta-ai/letta-code/capturing-tui-visual-proof"><img src="https://agentmods.dev/badge/skills/letta-ai/letta-code/capturing-tui-visual-proof.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 54 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00052 | $0.01312 |
| Opus 5.5 | $0.00021 | $0.00525 |
| Sonnet 5.5 | $0.00010 | $0.00262 |
| Haiku 4.5 | $0.00005 | $0.00131 |
Grade C, and why
capturing-tui-visual-proof scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "$before" How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capturing TUI Visual Proof
Record the production TUI through bun run src/index.ts. Do not substitute a
mocked Ink component, text fixture, generated image, or headless output for the
real terminal workflow.
Choose the Proof
- Static rendering change: capture before/after screenshots.
- Interaction or state transition: capture before/after GIFs.
- Timing or animation claim: record continuously; do not hide the interval that proves the claim.
Keep every variable except the code revision identical: terminal dimensions, theme, agent, model, prompt, fixtures, and CLI flags.
Prepare Exact Before and After Checkouts
Use the PR's base SHA rather than current main, which may have advanced:
repo=$(git rev-parse --show-toplevel)
pr=1234 # replace with the PR number
base=$(gh pr view "$pr" --json baseRefOid --jq .baseRefOid)
before=/tmp/letta-code-pr-$pr-before
rm -rf "$before"
git clone --shared --no-checkout "$repo" "$before"
git -C "$before" checkout --detach "$base"
For a dependency-neutral change, reuse the current checkout's dependencies:
ln -s "$repo/node_modules" "$before/node_modules"
If the PR changes dependencies, install them independently in each checkout
instead. Never install through a symlinked node_modules.
Make the Interaction Deterministic
Use the same existing test agent and a new conversation for both runs. For skill-loading proof, create a small temporary project skill with a fixed reply:
proof_skills=/tmp/letta-code-pr-$pr-skills
mkdir -p "$proof_skills/pr-proof-demo"
cat > "$proof_skills/pr-proof-demo/SKILL.md" <<'SKILL'
---
name: pr-proof-demo
description: Loads deterministic instructions for TUI visual proof.
---
After loading this skill, reply exactly: `Skill loaded.`
SKILL
Dry-run the flow in each checkout before recording:
bun run src/index.ts \
--agent "$AGENT_ID" \
--new \
--no-system-info-reminder \
--reflection-trigger off \
--skills "$proof_skills" \
--skill-sources project
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.
- 2mo ago First seen · 180 lines · 52 tokens per session scan C bbea3dff9d0b
capturing-tui-visual-proof is a skill published in the GitHub repository letta-ai/letta-code (3,730 stars, last pushed today), licensed Apache-2.0. It adds 52 tokens to every session and 1,312 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
memory-to-skill
Turn workflows from your MemSearch memory into reusable skills. Use when the user asks to make/create/extract/distill a skill from what they just did or from past work, review skill candidates, install a distilled skill, or 'turn this into a skill'. Manages MemSearch procedural-memory candidates under…
code-review
Review a diff against its acceptance criteria in four segments (convention adherence, bug scan, historical-context regressions, test-coverage gaps) as a NON-implementing agent. Findings are sorted by severity, each with file:line + a failure scenario. A planted defect must be caught; a clean diff must not be…
design-review
Five-dimension design audit (frontend UI/UX · server data-model & flow · endpoint spec · daemon-runtime/SDK & local-cache-first · built-in skill/agent-role), executed by a NON-implementing agent. Every dimension gets a verdict; N/A only with a stated reason. A dimension the design silently skipped must be surfaced as…
codebase-design
Design maintainable module interfaces, review scoped code changes, and simplify implementations with behavioral verification. Use for code review, cleanup, testability, and module design work.
prismer-github
GitHub via gh CLI: PRs, issues, reviews, repos, auth.
pr-body
A tool that reviews all commits on the current branch and creates or updates a pull request title and description. A pull request is a proposed code change submitted for review.