feat: working TOM agent

This commit is contained in:
2026-10-21 19:47:12 +01:00
commit efe543e6e2
83 changed files with 11779 additions and 0 deletions

View File

@@ -0,0 +1,51 @@
---
name: operating-chain
description: >-
The data files of a target operating model and how each traces to the one before:
operational requirements, capabilities, the Target operating model graph,
findings and verdicts. Use when writing or checking any of these files, and
whenever a submission is refused for a missing link.
---
# The operating chain
Every Deliverable of a target operating model carries a data file. Each entry has an id, and each file names the ids of the file before it. A submission is refused while a link is missing, and the refusal says which.
```
operating spec solution.items (S-n), solution.conditions (K-n),
intent.requirements, and its settled fields
│
operational-requirements.json OR-n source: a stated requirement, a Condition, or a field
│
capabilities.json C-n serves: OR ids items: S ids
│
target-operating-model.json parties P-n, roles R-n,
responsibilities RS-n capability: C id, role: R id
measures M-n outcome: BO id measured_by: C id
checks OC-n on: C, R or RS id source: OR or K id
│
verdicts.json a verdict on every OC id
```
## What is refused
| File | Refused when |
| --- | --- |
| `operational-requirements.json` | A requirement has no `source`, or names one that is not a stated requirement, a Condition or a settled field. A stated requirement or a binding field is carried by no requirement. |
| `capabilities.json` | A Capability names no catalogue entry and is not `custom` with a reason. It serves nothing, or names an id that does not exist. An Item is covered by no Capability. A requirement is served by none. A Capability that responds to faults is staffed for narrower hours than faults are responded to. Its effort is missing, or has no basis. |
| `target-operating-model.json` | A Role is in no Party, or in a country or at a level the rate card lacks, or outside the countries the customer allows. A Capability has no accountable Role, or more than one, or no responsible Role, or none that works its hours. A Condition is carried by no Check. A Check is on, or sourced from, something that does not exist. |
| measures, in `target-operating-model.json` | A business outcome the customer stated is shown by no Measure. A Measure shows an outcome that was not stated, or is taken by a Capability nobody is responsible for. Where the model measures how work flows, the outcome, guardrail and leading layers are not all measured. |
| `findings.json` | A finding lacks `lacks`, `proposed` or `needed_by`, names no Item of the solution under `about`, or names an id that does not exist. |
| `verdicts.json` | A Check has no verdict. A Check that depends on a finding passes: it is `not_verifiable` while the finding stands, or `fail` when the validator judges the operating model could meet it itself, such as by staffing or hours. |
## What code writes
Never write these yourself. They are computed from your data when you submit, so they cannot disagree with it:
- the responsibility matrix, the organisation chart (`organisation.mmd`) and the staffing and cost (`staffing.json`), from the Target operating model;
- the scenario walk-throughs (`scenarios.json`) and their verdicts, from the Target operating model and the operating spec;
- the verdict `waits_on_finding` on a Check that depends on a finding. The validator gives such a Check `not_verifiable`; it is recorded as waiting on its finding, and nothing is revised for it.
## Ids
Keep an id for as long as the thing it names exists. In a Change request an unchanged entry keeps its id and its text; a new one takes an id never used before; a removed one is left out. Never renumber.