agentleFS
Sign inStart free
tonydzitonydzi/second-brain-starter-kit/skills/precedent/SKILL.md

precedent

Skill6 starsChanged 2 months agoMITView on GitHub

Check whether something was already decided before proposing it: searches the decisions journal, the declined registry and the rules codex plus semantic search, and returns what was decided, why, what was rejected, and under what condition to revisit. Triggers: "/precedent <topic>", "did we already decide this".

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Before I propose a new field / script / structure / rule / automation (per show-before-after).

    line 40
  2. Distinctive:

    When the operator says "I think we discussed this".

    line 41
  3. Distinctive:

    Read-only: it only surfaces the past, it decides nothing for the operator.

    line 45

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/precedent — have we decided this already? (find the precedent before deciding)

Cheap insurance BEFORE a new structural choice or proposal: maybe there is already a verdict on this topic (accepted / rejected / deferred) — so we do not re-pitch something already declined, nor re-decide what is decided. This is the "RECALL before activity" rule applied to the DECISION layer.

What to pull up (cheap → expensive; stop as soon as you find it)

  1. The declined journal (first — the most frequent hit): memory $USERPROFILE/.claude/projects/<project>/memory/declined-decisions.md — what was rejected or deferred, why in the owner's own words, and Revisit-if (the condition under which it can come back).
  2. The accepted-decisions journal (vault): grep $OBSIDIAN_VAULT/02-Decisions/ (subfolders by domain) and any decision-* files in the vault.
    grep -rinl "<topic/keywords>" "$OBSIDIAN_VAULT/02-Decisions"
  3. The Bible (rules for all actors): grep reglament-* / protocol-* in the vault — maybe a standing rule already closes the question.
  4. Semantic top-up (if the exact grep is empty but the topic was clearly discussed): the /ask skill (RAG over the vault) — it catches phrasings grep missed.

What to give back to the operator

A short verdict, not a dump:

  • A precedent EXISTS → what was decided · when · why · a link to the note. If it was REJECTED, name the Revisit-if: reopen ONLY if the condition is met, or explicitly as a trade-off ("there is no other way") — never silently re-pitch.
  • No precedent → say exactly that: "I found no decision on this" (after checking the RIGHT drive/folder — an empty result is often "looked in the wrong place", not "no data"), and then go decide from scratch (for strategic questions, via the Alpha Protocol R+DR).

When to call it

  • Before I propose a new field / script / structure / rule / automation (per show-before-after).
  • When the operator says "I think we discussed this".
  • At the start of the Alpha Protocol — as part of the RECALL step.

Boundaries

  • Read-only: it only surfaces the past, it decides nothing for the operator.
  • It does not duplicate the Alpha Protocol — it is that protocol's narrow sub-step "is there already a verdict"; a full strategy still needs R+DR.
<!--kit-footer-->

Like this skill? It is one of 100 in second-brain-starter-kit: the second brain we built for ourselves and run every day at Palo Alto AI Research Lab. Install the whole set with npx skills add tonydzi/second-brain-starter-kit. Everything is open source and free, so take what you need.

Flagships worth a look on their own: secondop-panel (a second opinion from a panel of external models), claude-memory-tidy (stop your agent's memory from rotting), telegram-mcp-kit (your own Telegram over MCP in about 15 minutes).

Author: Anton Dziatkovskii, Palo Alto AI Research Lab. Telegram @tonydzi - WhatsApp +1 341 222 9178 - X @Tony_Stef_

Engineers: want to test-drive this setup? Message me. I hand out free starter seeds to engineers who test and report back, and custom skill requests are welcome.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free