Lockedin Capture

What it does

When your agent uses it

• Signals explicit capture intent from their current work session
• After a successful ingest where new entities are being proposed
• Says remember this
• Add this to my vault

Example prompts

• “save this”
• “log this”
• “track this”
• “/lockedin-capture”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Schema conformance — required fields populated correctly.
2. 2Edge completeness — all inferable edges from EDGE_SCHEMAS present.
3. 3Field specificity — values carry concrete information; no placeholders.
4. 4Semantic accuracy — entity types match the user's stated intent.
5. 5Duplicate detection + reconciliation — candidates surfaced and

What it can do on your machine

Read from SKILL.md and the folder at commit 02d8766. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md.

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Lockedin Capture loads about 1.4k tokens when it runs. Until then it costs about 170 tokens; SKILL.md has 447 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~170

When it runs · the whole SKILL.md, loaded when a task matches

~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• WarningTells the agent its actions are pre-authorized / not to stop for confirmationSKILL.md:110

  vault without asking the user first.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from daypunk/LockedIn at commit 02d8766, republished under its MIT licence (© daypunk). 447 words, ~1,430 tokens.

name

lockedin-capture

description

Converts in-session capture intents ("save this", "log this", "track this", "absorb this") into structured vault entries via a two-turn writer/reviewer pattern with duplicate detection and reconciliation. Writer proposes entity/edge structure; reviewer scores against five rubric dimensions and surfaces duplicate candidates for user decision. Activate when the user signals explicit capture intent from their current work session, or after a successful ingest where new entities are being proposed. Also activate when the user says "remember this", "capture this", "add this to my vault", or describes something they just shipped, learned, decided, or discussed.

User input
    │
    ▼
1. Writer turn (prompt-writer.md)
   - Read user input + any provided context
   - Propose entity types, fields, edge structure
   - Run _infer_edges() mentally from EDGE_SCHEMAS domain/range
   - Quote source phrases from user input
   - Output: structured proposal (markdown table)
    │
    ▼
2. ValidatorDeterm (lockedin validate --dry-run)
   - Deterministic field-type and required-field check
   - Catches schema errors before LLM reviewer sees the proposal
    │
    ▼
3. Reviewer turn (prompt-reviewer.md) — SEPARATE Claude context
   - Re-load RUBRIC.md fresh (not from writer-turn memory)
   - Score 5 dimensions independently
   - Query vault for duplicate candidates (slug similarity, alias match)
   - Output: JSON score + candidates + suggested revisions
    │
    ▼
4. ReconcileNegotiator (if duplicates surfaced)
   - Present candidates to user as a numbered list
   - Ask one question: merge / update / create new
   - Never auto-merge, never auto-create-duplicate
    │
    ▼
5. write-before-confirm
   - State what will be written: "Saving 2 entries — meeting X, decision Y. OK?"
   - On confirmation: call write_entity for each proposed entity
   - Edges written atomically with entities

SKILL.md            (this file)
RUBRIC.md           5 dimensions; score bands; fixture authoring guide
prompt-writer.md    writer-turn instruction
prompt-reviewer.md  reviewer-turn instruction (separate Claude context)
AGENTS.md           four agents: Writer, ValidatorDeterm, Reviewer, ReconcileNegotiator
TOOLS.md            deterministic tools the skill uses
banned_phrases.json phrases that indicate low-quality field values
research-notes.md   sources informing capture design rationale

© daypunk, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 7 other files in plugins/lockedin/skills/lockedin-capture of daypunk/LockedIn.

• SKILL.md
• AGENTS.md
• RUBRIC.md
• TOOLS.md
• banned_phrases.json
• prompt-reviewer.md
• prompt-writer.md
• research-notes.md

Open the folder on GitHubat commit 02d8766