institutional-memory-distill

institutional-memory-distill is a skill for Claude Code, Codex from linkpranay-ai/context-engineering-protocol. It costs 89 tokens per session (3,941 once invoked), scanned A, original, Apache-2.0.

A tool for extracting past decisions, their reasoning, and rejected options from pull requests, design documents, and postmortems into a searchable project record.

In plain words
What is it for?
Use it to record institutional knowledge from project history so later coding work can be checked against those decisions.
Why use it?
It helps teams avoid reopening settled debates or repeating approaches that already failed because the original reasoning is easy to forget.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to record institutional knowledge from project history so later coding work can be checked against those decisions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/linkpranay-ai/context-engineering-protocol/ult-institutional-memory-distill
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.

Any agent
npx skills add linkpranay-ai/context-engineering-protocol --skill ult-institutional-memory-distill
Clone the repo
git clone --depth 1 https://github.com/linkpranay-ai/context-engineering-protocol

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for institutional-memory-distill

README.md
[![agentmods](https://agentmods.dev/badge/skills/linkpranay-ai/context-engineering-protocol/ult-institutional-memory-distill/github.svg)](https://agentmods.dev/skills/linkpranay-ai/context-engineering-protocol/ult-institutional-memory-distill)
Your own site
<a href="https://agentmods.dev/skills/linkpranay-ai/context-engineering-protocol/ult-institutional-memory-distill"><img src="https://agentmods.dev/badge/skills/linkpranay-ai/context-engineering-protocol/ult-institutional-memory-distill/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.

agentmods 80×15 button for institutional-memory-distill

Your own site · 80×15
<a href="https://agentmods.dev/skills/linkpranay-ai/context-engineering-protocol/ult-institutional-memory-distill"><img src="https://agentmods.dev/badge/skills/linkpranay-ai/context-engineering-protocol/ult-institutional-memory-distill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,941 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00089 $0.03941
Opus 5 $0.00044 $0.01971
Sonnet 5 $0.00018 $0.00788
Haiku 4.5 $0.00009 $0.00394

Measured 9d ago against content hash 2b0cfcd8866e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

institutional-memory-distill 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 9d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/decision_ledger.py, scripts/tests/test_decision_ledger.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.github/skills/ult-institutional-memory-distill/SKILL.md · 281 lines

How it starts

The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Distilling Institutional Memory (Trip-Wire)

Overview

Codebases accumulate decisions faster than anyone can remember them: "we tried Redis here and reverted it," "legal blocked this vendor once already," "the team already decided against a global feature flag and re-litigates it every few months." That reasoning usually lives — once — in a merged PR's description, a design doc's "Alternatives Considered" section, or a postmortem's root-cause writeup, and then it's gone. Nobody re-reads six-month-old PRs before starting new work, so the same rejected path gets proposed again, argued again, and sometimes shipped again before someone remembers why it didn't work last time.

This skill is the distillation half of trip-wire: it reads a project's own PR history, design docs, and postmortems, and turns decisions with reasoning — not just decisions — into structured, queryable entries in the project's decision_ledger. The query half lives in ult-context-generate/SKILL.md Step 7.7, which checks every new context package's aspects against this ledger and surfaces a revise/proceed/escalate hit when something the ledger already knows about overlaps the new work.

Run this:

  • Once, early in a project's life, to backfill the ledger from existing history
  • Again periodically, or on demand ("distill decisions from the last 20 merged PRs") — it is fully re-runnable; see "Idempotency" below

Output: entries, cursors, tombstones, and (indirectly, via ult-context-generate) dispositions in the decision_ledger path-slot — resolved via ult-repo-layout/SKILL.md's path-resolution algorithm, same mechanism as compiled_guidelines. Pre-D21 default: starter_kit/decision_ledger/DECISION-LEDGER.json; once layout.workspace_root is set: {workspace_root}/cache/decision-ledger/DECISION-LEDGER.json (a derived, script-owned artifact — see layout-slots-registry.yaml's decision_ledger entry for the bucket-reassignment rationale, same pattern as compiled_guidelines). Resolve it once per run and substitute it for the pre-D21 default everywhere below.

Read the full file on GitHub · 281 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 281 lines · 89 tokens per session scan A 2b0cfcd8866e

Subscribe to this mod's changes

institutional-memory-distill is a skill published in the GitHub repository linkpranay-ai/context-engineering-protocol (8 stars, last pushed yesterday), licensed Apache-2.0. It adds 89 tokens to every session and 3,941 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

carryover

Use when recalling, saving or curating carryover memory, wikis, playbooks or the Obsidian vault.

Cfvillarroel/carryover · 27 tokens

bootstrap-llm-synthesis

Construct the LLM synthesis prompt from project surface scan + optional tree-sitter context + optional Q&A answers. Call the LLM. Parse and validate the response into 6-8 structured memory entries with clarity tags and source traceability. Used as Stage 3 of the /gaai:bootstrap pipeline.

digipulse-engineering/GAAI-framework · 69 tokens

memory-reconcile

Scan all memory files, documentation (/docs//.md), and README files (/README.md) for drift, contradictions, and stale references. Produce a reconciliation report for Discovery to action. Activate on demand or via cron.

digipulse-engineering/GAAI-framework · 0 tokens

memory-archive-superseded

Migrate a superseded DEC's index rows from active index.md to archive/superseded-decisions.archive.md. Idempotent. Discovery-only — never invoked by daemon delivery. Updates DEC frontmatter as canonical source of truth.

digipulse-engineering/GAAI-framework · 58 tokens

memory-delta-triage

Apply three deterministic heuristics to a single memory-delta file to produce a structured verdict block; invoke memory-ingest on ACCEPTED candidates only in validate mode. Activate when Discovery processes a raw memory-delta from contexts/artefacts/memory-deltas/.

digipulse-engineering/GAAI-framework · 58 tokens

decision-extraction

Identify and formalize durable product and technical decisions from agent outputs into long-term memory. Activate after Discovery produces artefacts, Delivery resolves trade-offs, or product direction materially changes.

digipulse-engineering/GAAI-framework · 39 tokens