reply-team/jason-ai / skills/business/sdr-operations
sdr-operations
Verifiedreferences/catalog-17-oversight.md
View on GitHub<!-- Generated. Do not edit by hand. -->
# Family 17 — Oversight, review and safety
Generated from the contract fragments in `operations/`. Edit a fragment, not this file.
*The organisation around the work* · 32 operations · contract 2.0.0
**Reading the table.** † marks a core operation. The five properties are *reach*
(`read` changes nothing · `control` changes state we own · `act` reaches the outside world),
*reversibility* (`reversible` · `compensatable` · `irreversible`), *approval*
(`auto` · `confirm_once` · `confirm_each`, derived from reversibility × reach), *before repeating*
(the observable state to read before running it again) and *cost* (`none` · `metered`, with its
basis and the meter it consumes). *Key* and *per-item* are the two standing obligations: an
idempotency key on every act, every metered call, every write accepting a collection and every
write creating a durable object. A write that takes no key says why in *exempt* — `absolute_valued`
(the same value written again), `terminal_state` (the same state arrived at again), or `unstated`,
which is the contract admitting it has no reason and not a claim that one exists. And one outcome
per item whenever a collection is carried. Where a property is conditional the cell holds the
dangerous reading, with the condition beneath it.
| Operation | Intent | Reach | Reversibility | Approval | Before repeating | Cost | Key | Per-item | Invariants |
|---|---|---|---|---|---|---|---|---|---|
| `approval.request`<br>*questions:* 4 | "Put something in front of a human and wait" — a message about to go, a bulk write, a piece of content, a policy change. | `control` | `reversible` | `auto` | the pending queue for this subject and artefact; a request already pending is not a reason to raise a second one. | `none` | `required` | `required` | `L1`, `L4` |
| `approval.list` † | "What is waiting for a human to look at, and how long has it been waiting?" | `read` | `reversible` | `auto` | nothing at stake | `none` | `none` | `required` | `L1`, `L2` |
| `approval.get` | "Show me this one item exactly as it will go out, with the reasoning behind it" | `read` | `reversible` | `auto` | nothing at stake | `none` | `none` | `not_applicable` | `E14` |
| `approval.resolve` † | "Approve this, or reject it with a reason." Approving is the send. | `act`<br>*conditional:* `act` on approve, `control` on reject. | `irreversible`<br>*conditional:* irreversible on approve, reversible on reject. | `confirm_each`<br>*conditional:* confirm_each on approve, confirm_once on reject — and the resolution is the confirmation when a human performs it directly. | the item's state; a resolved item must never resolve twice, and a timed-out approve may already have sent. | `none` | `required` | `required` | `I5`, `L1`, `L3`, `L4`, `L5` |
| `autonomy.get` | "What may this agent currently do without asking, in this scope, on this channel — and where does the gate live?" | `read` | `reversible` | `auto` | nothing at stake; re-read at the start of every unattended run. | `none` | `none` | `required` | `L1`, `N5` |
| `autonomy.set` | "Set what runs unattended and what stops" — the gate, the mode, the queue timeout and what a timeout means, the unattended action cap, the escalation target, and which channels are treated differently. | `control` | `reversible` | `confirm_once`<br>*departs:* raised, because the acts permitted under a loosened setting are not reversible even though the setting is. | the current setting for the scope, and whether an unattended run is in flight under the old one. | `none` | `none`<br>*exempt:* `absolute_valued` | `required` | `B13`, `H12`, `K9`, `L1`, `L2` |
| `escalation.raise`<br>*questions:* 4 | "I cannot or must not proceed; a named human owns this now" — explicitly not an approval, because nobody is granting permission. | `control` | `compensatable` | `auto` | open escalations for this subject; an open one is a reason to add context, not to raise a second. | `none` | `required` | `required` | `L1`, `L4`, `L8` |
| `escalation.list` | "What has been handed to a human and not yet picked up, and how old is it?" | `read` | `reversible` | `auto` | nothing at stake | `none` | `none` | `required` | — |
| `escalation.resolve`<br>*questions:* 22 | "Record how it ended, and whether the work comes back to the agent or stays with the human" | `control` | `reversible` | `auto` | the escalation's state | `none` | `required` | `required` | — |
| `editorial_review.record` | "A named human read this machine-drafted message, changed what they changed, and let it go" — bound to the message actually sent, with the editor, the time and the difference from the draft. | `control` | `irreversible` | `confirm_once` | whether a review is already bound to this sent message; two reviews of one send is an unresolvable evidence record. | `none` | `required` | `required` | `A21`, `E14` |
| `editorial_review.get` | "Show me the human review behind this message that went out — or tell me plainly that there is none" | `read` | `reversible` | `auto` | nothing at stake; `none` is a first-class answer and the one an auditor most needs. | `none` | `none` | `required` | `A21` |
| `review.request` | "Put a call, a sent message or an unsent draft into someone's review queue" — mine going out for feedback, or a manager's going to a named reviewer. | `control` | `reversible` | `auto` | the pending review queue for this artefact | `none` | `required` | `required` | — |
| `review.list` | "The review queue: what is waiting, what is done, by person and by period" | `read` | `reversible` | `auto` | nothing at stake | `none` | `none` | `required` | — |
| `review.get` | "One review in full" — the answers, the scorecard version used, who was scored, who scored, and whether I am entitled to see it. | `read` | `reversible` | `auto` | nothing at stake; a refusal to show a score is a correct answer, not a failure. | `none` | `none` | `not_applicable` | `L9` |
| `review.score` | "Score an artefact against a published scorecard" — recording who was scored, who scored, and which version was used. | `control` | `reversible` | `auto` | existing scores on this artefact for this scored person; a machine-assigned score never overwrites a human one. | `none` | `required` | `required` | `H3`, `L9` |
| `feedback.record` | "I have actually spoken to them about it" — scored and told-them are different facts and only one changes behaviour. | `control` | `reversible` | `auto` | whether feedback is already marked given for this review. | `none` | `required` | `required` | — |
| `review_policy.define` | "State which completed work gets reviewed, at what sample rate, how far back, and by whom" | `control` | `reversible` | `auto` | the policy currently in force | `none` | `none` | `not_applicable` | — |
| `review_policy.get` | "What is the review policy in force, and what coverage does it actually imply?" | `read` | `reversible` | `auto` | nothing at stake | `none` | `none` | `not_applicable` | — |
| `scorecard.define` | "The questions, their types and their weights, with the arithmetic stated out loud" | `control` | `reversible` | `auto` | the current draft and its publication state | `none` | `none` | `not_applicable` | `L9` |
| `scorecard.list` | "What scorecards exist, which are published, and what is each scoped to?" | `read` | `reversible` | `auto` | nothing at stake | `none` | `none` | `required` | — |
| `scorecard.publish` | "Make this version usable for scoring" | `control` | `reversible` | `confirm_once`<br>*departs:* raised, because every score taken afterwards carries this version and past scores must stay comparable. | the scorecard's publication state and version | `none` | `none` | `not_applicable` | — |
| `scorecard.retire` | "Take it out of use for new scoring" — everything already scored keeps its history. | `control` | `reversible` | `confirm_once`<br>*departs:* declared confirm_once where control × reversible derives auto, and the contract does not yet state why. The row's own terms are that it can be published again and everything already scored keeps its history, so the raise stops at one confirmation. Kept at the declared, stricter class until the question is settled: an unexplained confirmation costs a sentence, and lowering a class on a guess costs whatever relied on it. | the scorecard's publication state | `none` | `none` | `not_applicable` | — |
| `coaching.summarize` | "Per coach, per period: how much coaching actually happened" — attended, listened, commented, scored, feedback given. | `read` | `reversible` | `auto` | nothing at stake | `none` | `none` | `required` | — |
| `budget.get` | "What allowance is left on this meter, in this scope, for this period?" | `read` | `reversible` | `auto` | nothing at stake; `unknown` is a real answer, and unknown remaining allowance is not the same as ample remaining allowance. | `none` | `none` | `required` | `A6`, `C5`, `F3` |
| `budget.set` | "The ceiling the pre-flight check reads" — a hard stop, not an alert. | `control` | `reversible` | `confirm_once`<br>*departs:* raised whenever it raises a ceiling, because the spending it then permits is not reversible. | the ceiling in force and the consumption against it | `none` | `none` | `not_applicable` | `C3`, `C5` |
| `stoprule.set` | "The condition that stops the work by itself" — what is measured, over what window, at what threshold, and what it halts. | `control` | `reversible` | `auto` | the rules already in force for this scope; two rules on one subject is usually a mistake, not belt and braces. | `none` | `none` | `not_applicable` | `C5`, `L6`, `L8` |
| `stoprule.list` | "What stop rules are in force right now, over what scope, and what would each halt?" | `read` | `reversible` | `auto` | nothing at stake | `none` | `none` | `required` | — |
| `stoprule.clear`<br>*questions:* 25 | "Remove a stop rule" | `control` | `reversible` | `confirm_once`<br>*departs:* raised, because removing a safety rule is exactly the write that should never happen by accident. | the rules in force, and whether this rule is currently in a fired state. | `none` | `none`<br>*exempt:* `unstated` | `required` | `L6` |
| `stoprule_firing.list` | "What has fired, when, on what measured value, and what is still stopped because of it?" | `read` | `reversible` | `auto` | nothing at stake; this is the read that tells the next session why sending is off. | `none` | `none` | `required` | `J5`, `L8` |
| `stoprule_firing.get` | "One firing in full" — the rule, the value that tripped it, the operations halted, and every item left unprocessed. | `read` | `reversible` | `auto` | nothing at stake | `none` | `none` | `required` | `J5`, `L8` |
| `outreach.hold` †<br>*questions:* 10 | "Stop everything for this person, this company or this domain, now" — the kill switch. | `control` | `compensatable` | `auto` | no active enrolment, no open task, no pending approval, no un-accepted handoff, no outstanding meeting proposal and no scheduled message for anyone in scope. | `none` | `required` | `required` | `H9`, `I5`, `L6` |
| `outreach.release` | "Lift a hold" | `control` | `compensatable` | `confirm_once`<br>*departs:* raised, because a restart resumes contact with people whose situation may have changed while they were held. | the hold's per-item ledger and each person's current eligibility. | `none` | `required` | `required` | `A7`, `E3`, `G5`, `L6` |
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |