flag
Record an observation about plasticity memory for evaluation, e.g.
Skill by vhavlena
Chalk Labs
Need help deploying flag?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/vhavlena-flag
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Nov 2, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/flag
Tools it pre-approves 2
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
Bash(plasticity*)
What's inside
- Skill name
flag- Description
- Record an observation about plasticity memory for evaluation, e.g. /plasticity:flag miss it forgot we pinned schema 6
- License
- Apache-2.0
- Allowed tools
- Bash(plasticity, *)
- Instructions
- 25 lines in SKILL.md · view on GitHub
Before installing
- Pre-approves some shell commands
Files (1)
- SKILL.md
SKILL.md (first lines)
Run every `plasticity` command below with the `--db` prefix given at session start (`plasticity --db '...'`), so it uses this session's memory. The user is evaluating the long-term memory and flags an observation: $ARGUMENTS 1. Kind: the first word if it is `miss`, `noise`, `helped` or `other`; otherwise infer it: - `miss`: something stored was not recalled when it should have been; - `noise`: an injected memory was irrelevant; - `helped`: a memory clearly helped; - `other`: anything else. 2. Neurons concerned: IDs of the memories involved, if you can tell them from the injected `<plasticity-memories>` or your recalls in this session. For a miss, find the memory that should have been recalled with `plasticity search "<keywords>"` and name it too. 3. Run: ```sh plasticity note -k <kind> --session <SESSION_ID> [--id <ID> ...] "<the user's observation, plus one line of context: the prompt or task it was about>" ``` (the session ID was given at session start). Confirm in one line. Do not change the memory itself: the note is evidence for tuning. If the user also wants a wrong memory fixed, do that separately.
From vhavlena/plasticity, Apache-2.0.
More from vhavlena/plasticity
- 0.565score
memory
vhavlena
Long-term memory (plasticity knowledge graph).
SkillAFreshness: AClaude Code +9 - 0.556score
remember
vhavlena
Store something in plasticity long-term memory, e.g.
SkillAFreshness: AClaude Code +9 - 0.553score
recall
vhavlena
Search plasticity long-term memory, e.g.
SkillAFreshness: AClaude Code +9 - 0.553score
setup
vhavlena
Check and configure plasticity long-term memory (build, semantic search, scope)
SkillAFreshness: AClaude Code +9 - 0.553score
graph
vhavlena
Open an interactive visualization of plasticity long-term memory (the knowledge graph) in the browser
SkillAFreshness: AClaude Code +9 - 0.553score
status
vhavlena
Show the state of plasticity long-term memory (size, semantic search, recent activity)
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 11, 2026 (26 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/vhavlena/plasticity
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from vhavlena
- 0.565score
memory
vhavlena
Long-term memory (plasticity knowledge graph).
SkillAFreshness: AClaude Code +9 - 0.556score
remember
vhavlena
Store something in plasticity long-term memory, e.g.
SkillAFreshness: AClaude Code +9 - 0.553score
recall
vhavlena
Search plasticity long-term memory, e.g.
SkillAFreshness: AClaude Code +9 - 0.553score
setup
vhavlena
Check and configure plasticity long-term memory (build, semantic search, scope)
SkillAFreshness: AClaude Code +9 - 0.553score
graph
vhavlena
Open an interactive visualization of plasticity long-term memory (the knowledge graph) in the browser
SkillAFreshness: AClaude Code +9 - 0.553score
status
vhavlena
Show the state of plasticity long-term memory (size, semantic search, recent activity)
SkillAFreshness: AClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get flag running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
flag skill. Agent Mart. https://agentmart.dev/skills/vhavlena-flag (last updated 2026-10-24)