Skip to content
Skills Library
Management & product · Planning

mode-selection

/mode-selection

Use when choosing the operator-approved `mode` (`project` versus `bounty`) before launch—approval of the work does not approve that workflow. Not for constructing fields or reviewer routing.

Licence
MIT
Last repository change
20.09.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 20.09.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Use when choosing the operator-approved `mode` (`project` versus `bounty`) before launch—approval of the work does not approve that workflow. Not for constructing fields or reviewer routing.

Original author description

Use when choosing the operator-approved `mode` (`project` versus `bounty`) before launch—approval of the work does not approve that workflow. Not for constructing fields or reviewer routing.

How it works

  1. Name the mode and get approval — it is its own consent
  2. Both dispatch paths preserve an explicit choice
  3. Verify the mode that LANDED, never the one you intended
  4. The mode changes the contract, not just the wall
Original SKILL.md headings · 54 lines, 521 words
SKILL.md preview
---
name: mode-selection
audience: chrono
description: Use when choosing the operator-approved `mode` (`project` versus `bounty`) before launch—approval of the work does not approve that workflow. Not for constructing fields or reviewer routing.
---

# Mode Selection

House procedure for choosing a dispatch mode before authoring the packet. The mode is a separate
operator decision from the work itself, and the wrong mode silently changes the wall, the
verification contract, and the gates a lane runs under. Verify every claim here against the current
scripts — do not trust this doc over the code.

## Name the mode and get approval — it is its own consent
- `chrono/CLAUDE.md` Dispatch step 1 requires opening the chosen file under `shared/modes/`, stating
  which mode the work will run under, and waiting for the operator to agree. Hard Rule 1 forbids a
  mode starting without explicit consent.
- **Approving the work is not approving the mode.** A convenience wrapper's silent default sent
  most of a campaign's lanes under a mode nobody chose — without telling the operator. Say the mode
  word out loud; never infer it from "yes, go".

## Both dispatch paths preserve an explicit choice
- Generated packets use `scripts/send-task.sh ... --mode project|bounty`. The wrapper rejects an
  omitted or invalid value, writes the exact choice into frontmatter, and never supplies a default.
- Prepared packets carry `mode: project|bounty` in frontmatter and dispatch with
  `bin/send-task.sh <packet-file>`, which carries the packet's own `mode` into the compiled contract
  (`MODE_VALUE` -> `"mode"`).
- The wrapper survives because it still assembles standard frontmatter, resolves lanes and review
  metadata, and routes through the hardened dispatcher. Retire it only if those conveniences move
  elsewhere; do not retain or reintroduce a mode default as its reason to exist.

## Verify the mode that LANDED, never the one you intended
- The dispatch context carries the landed mode as a real field. Read it from the **exact attempt you
  dispatched**, never from a glob — attempt ids are UUIDs, so glob order is not chronological and
  `head -1` can hand you a previous attempt's mode after a retry:
  ```bash
  python3 -c 'import json,sys; a=json.load(open(sys.argv[1]))["authority"]; \
    p=a.get("mode_profile"); m=(a.get("memory_context") or {}).get("mode"); \
    print(p if p==m else f"MISMATCH profile={p} memory={m}")' <context_path>
  ```
  `mode_profile` and `memory_context.mode` must agree; if they disagree, stop — do not pick one.
- A wrapper `--dry-run` echoes `Packet mode: <mode>` and derives that mode's contract. It proves the
  generated packet's choice but not a landed attempt; a green prepared-packet dry-run likewise does
  not replace the exact-attempt check.
- If the landed mode differs from what the operator approved, stop and say so before the lane works.

## The mode changes the contract, not just the wall
- Walls come from `timeout_budget_for_mode()` in `dispatch_context_builder.py`: a flat 2700s for
  `project`, 3600s for `bounty`. Scope to the emitted number; do not infer it from a ratio.
- `verification_contract.py` sets a different contract per mode. `project` requires
  `project_tests`/`recipient_contract` and mandatory recall+record. `bounty` swaps in
  `scope_gate`/`no_self_inflicted`/`poc_reproduction`, an exact target allowlist, forbids
  submission-attempted, and makes recall OPTIONAL (a cold lane cannot recall without inheriting other
  runs' conclusions).
- `project` and `bounty` both carry a `plan_review_policy` with `anti_affinity: author_family` — an
  independent-family plan check is part of the contract. That is the controller's plan review and is
  separate from the deliverable's own `review_model`; a `project` packet with `review_model: none`
  still launches.

Versions

The database has no other skills named mode-selection.

Database snapshot: 13.11.2026 · package version 6f835286e15b (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100bounty-qualifier
    Qualifies open AI-agent code bounties by expected value before any effort is spent. Use when a bounty feed returns options and you need to pick one, compare boards on a single value scale, or decide whether a board is worth continuing. Computes EV = (net_reward x…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.