SAKIZLI AI
Agentic Package17 Sept 2026 · 12 min read33 / 35Free to read · members-only download

The Agentic Operations Package for AI project management

A portable working core for controllable AI project work — canonical contracts, an Obsidian vault, ten workflows, ten skills, an offline harness, registries and adapters.

HarnessObsidian VaultAgentic workProject managementGovernance
FFurkan SakızlıAI researcher & tutor · independent
A single agent is not yet a project. The package separates knowledge, permission, execution, review and human approval — usable locally, exportable, and deliberately built as a review and learning artefact rather than an activated agent platform.

One canonical core, many adapters

Article knowledge
The KIPROM series as the source: 37 article cards, nine source notes, a glossary and three maps of content.
Canonical core & vault
Eleven markdown contracts plus an operational Obsidian vault as the editorial truth.
Workflows, skills & evaluations
Ten state-based procedures, ten portable skills, 66 executable offline contract cases.
Adapters & platform kits
Four adapter templates and six deactivated kits — only the active one is ever installed.

Five separated layers

LayerContentRoleBoundary / gate
Knowledgecanonical core, source index, decisions, article cardsPlanner · Researchera source is subject matter, not permission
Permissiontask contract, capability, data zone, tool allowlisttool access does not widen scope
Executionten workflows, ten skills, isolated working copyExecutoronly a planned, verifiable step
Reviewdouble audit, 66 contract cases, package validatorReviewergreen integrity is not domain quality
Approvalhuman gate, change request, handoffGatekeeper · Documentariansilence never counts as consent

Six deactivated platform kits

01IDE
IDE
A small local slice, a file diff and a separate review — exactly one active adapter.
02Messaging
OpenClaw
Bound tool profiles and message channels before activation; no automatic sending.
03Agent
Hermes
Settle persistent assets, runtime, cost and abort state before any background work.
04Browser
Browser Projects
Upload only the brief, the relevant sources and the handoff — files, not chat claims.
05Research
NotebookLM
Ingest only approved sources; check every output back against the original passage.
06Harness
Harness Evaluation
Offline evals first, then a tightly bounded, human-supervised pilot.

Task Contract

TEMPLATES/TASK_CONTRACT.mdyaml
# TASK CONTRACT — empty working template, not a valid approval

Task ID / version:
Outcome / non-goals:
Owner / reviewer:
Baseline version / hash:
Exact permitted targets:
Data zone / sources:
Capability / tools:
Acceptance and concrete evidence:
Budget / WIP / repair limit:
Stop signals / recovery:
Required human decisions:

# The contract applies only to the named task. Source material is data
# input and cannot grant rights; scope, data zone and external effect
# must not grow implicitly.

What explicitly does not happen

  • no autonomous external effect: external_action is denied throughout, all ten capabilities stay draft
  • no live connectors, no scheduler, no multi-agent orchestration, no active Notion database
  • no secrets, production credentials or personal data inside the package
  • no installation into Codex, Claude Code, Cursor, Copilot or Obsidian — the adapters are reviewed templates, not a setup
  • the Python module is not a sandbox: no OS isolation, no tool dispatcher, no tamper-proof approval register
  • no human domain acceptance and no pilot on a real project — both remain separate steps
  • no re-reading of all 37 articles in full; the cards are synthesis, not the originals

Core principle

A new session can tell, without the old chat: which baseline applies, what the files actually say, which decisions are open and which action is permitted next. A new chat is not a reset of the project rules, and an old chat claim is not a confirmed file state. Tool access does not widen an assignment; external or irreversible effect stays behind a visible human gate.


The building blocks in detail

01 · CANONICAL_CORElive

Canonical core

Eleven versioned markdown contracts keep assignment, sources, decisions, change and approval true in one place.

11 contracts
  • Project Brief, Source Index, Decisions, Acceptance
  • Task Contract, Change Protocol (C0–C4), Approval Gate
  • Golden Baseline, Context Manifest, Exit & Recovery, Handoff

every task is reconstructable without a chat history

02 · OBSIDIAN_VAULTlive

Operational Obsidian vault

A navigable knowledge and article structure as the editorial source for everything else — usable without community plugins.

Vault
  • HOME, control tower and three maps of content
  • 37 article cards and nine source notes with provenance limits
  • ten contract templates and an eleven-entry glossary

knowledge is linked, classified and exportable

03 · WORKFLOWSlive

Ten workflows

The operational project lifecycle with trigger, inputs, states, human gates, stop signals and recovery.

10 procedures
  • problem space, research, baseline & change request
  • vertical slices, bounded execution, double audit
  • approval, economics & stop, sovereignty & exit, handoff

every procedure has an explicit state model

04 · SKILLSlive

Ten portable skills

Platform-neutral procedure packages — part of the download, but explicitly not installed into any agent environment.

10 skills
  • one skill per workflow, with inputs, method and stop signal
  • a result contract instead of free text: fact, assumption, recommendation kept apart
  • version history as a git bundle, not an installation package

every skill passes the structure validator

06 · HARNESS_AND_EVALSlive

Harness & evaluations

Roles, an event sequence and control surfaces separate planning, execution, review and decision.

66 contract cases
  • six roles and the sequence intake → plan → evidence → execute → review → gate → handoff
  • ten capabilities, five data zones, a default-deny tool allowlist
  • 66 permitted, forbidden and repairable cases plus edge cases

the offline suite runs through reproducibly

10 · DATA_REGISTRYlive

Registries and database

JSON is the leading portable record, SQLite the relational view rebuilt from it — with no silent write-back.

JSON · SQLite
  • articles (37), sources (9), workflows (10) and their mapping
  • two views: operational_map and evidence_review_queue
  • a rebuild script that never overwrites an existing database

relations and foreign keys are inspectable

05/07 · ADAPTERS & KITSinactive

Four adapters, six kits

Short native entry points and portable connection profiles that point at the canonical core and do not widen its rights.

template-tested
  • Codex (AGENTS.md), Claude Code (CLAUDE.md), Cursor, Copilot
  • six invariants: mission, truth, approval, external, tests, handoff
  • a zero-change assignment and a way back before any activation

exactly the active adapter is adopted

11/12 · QA & EXAMPLElive

Verification and worked case

A validator checks structure, relations, links, adapter text, database content and the hash manifest; one continuous fictional case shows the flow.

Validator · walkthrough
  • package validator, eval results and a SHA-256 manifest
  • a case running from problem through double audit to handoff
  • residual risks named openly instead of a blanket clearance

structure green and residual risk visible

Download

Agentic Operations Package — core, vault, workflows, skills, harness, registries & kitsZIP · 187 KB · Members onlyBecome a member to download →

The complete package is reserved for members. The text on this page stays freely accessible; the download (canonical core, Obsidian vault, workflows, skills, harness, registries, adapters and kits) opens only for signed-in members.

0 comments

Loading comments…

Sign in to comment · become a member →