registry-digest

A command that summarizes recent completed or abandoned work from the FlightPlan team registry. It groups the work by theme and can also show currently active work.

In plain words
What is it for?
Creating a temporary digest for this repository, a time period, an author, an area of files, or topic words.
Why use it?
It saves developers from searching through individual registry entries to understand what the team has been doing.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/sledmonkey/getflightplan/registry-digest
Clone the repo
git clone --depth 1 https://github.com/sledmonkey/getflightplan

Made for: Claude Code.

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 484 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00011 $0.00484
Opus 5 $0.00005 $0.00242
Sonnet 5 $0.00002 $0.00097
Haiku 4.5 $0.00001 $0.00048

Measured 2d ago against content hash 459f3d90dd32, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

registry-digest 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.

.claude/commands/registry-digest.md · 43 lines

What it actually says

Produce an on-demand digest from the team intent registry (MCP server: flightplan). The output is ephemeral chat text — don't write it to a file or post it anywhere. (The registry's own /digest and /receipts pages are the standing narrative surfaces; this command is the on-demand, scoped variant.)

Scope (from $ARGUMENTS; all optional)

Default: this repo, last 14 days, everything.

  • A duration token (7d, 2w, 48h) → the time window (since).
  • author:<name> → only that person's intents (author).
  • Tokens containing / or * → area globs (pass as overlaps).
  • Anything else → topic words (pass as q).

Retrieval

Use list_intents with repo = the name pinned in .flightplan.toml at the repo root (fallback: basename of the git origin remote, else the repo root directory name). Fetch status="done,abandoned" for the narrative, and status="active" for the closing "in flight" section. For topic queries that come back thin, loosen before concluding nothing happened: retry with match="any", then with fewer words. Read the full outcomes — they are the source, not the summaries alone.

Synthesis rules

  • Group by theme, not chronology. Lead each theme with what changed and why.
  • Preserve the surprises, dead ends, and things deliberately left alone — that context is the payload; do not flatten the digest into a changelog.
  • Where an outcome records that a warn overlap changed the work (coordinated / narrowed / proceeded anyway), say so.
  • Cite intent ids (first 8 chars) so a reader can pull any full record.
  • Close with: what's in flight right now, plus open threads — abandoned work someone might resume, and anything declared uncommitted that may not have landed.
  • Length tracks activity: a quiet window gets a short digest that says so plainly. Never pad.
Changes

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.

  1. 2d ago First seen · 43 lines · 0 tokens per session scan A 459f3d90dd32

Subscribe to this mod's changes

registry-digest is a command published in the GitHub repository sledmonkey/getflightplan (2 stars, last pushed 9d ago), licensed Apache-2.0. It adds 11 tokens to every session and 484 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 2026-08-31.