architrave-tournament
Skill2 starsChanged 7 days agoMITView on GitHub
Explicitly compare implementation options when the user requests a tournament, or when viable options genuinely differ on material architecture, security, migration, data-loss, infrastructure or runtime risk, or a recurring failure needs a discriminating recovery. Not for routine bounded work.
In this repository14 other files it gives its agents.
- AGENTS.mdAGENTS.md
- architrave-agent-authoringSkill
- architrave-ctoSkill
- architrave-mcp-integrationSkill
- architrave-reviewSkill
- architrave-skill-authoringSkill
- architraveSkill
- architrave-workSkill
- skill-creatorSkill
- subagent-driven-developmentSkill
- systematic-debuggingSkill
- verification-before-completionSkill
- webapp-testingSkill
- writing-skillsSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 6
Use the current host's visible architrave:tournament-analyst role for an authorized comparison.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Use the current host's visible architrave:tournament-analyst role for an
authorized comparison. Supply the user request, acceptance criteria, governing
repository sources, constraints, evidence and unresolved assumptions. If the
role is unavailable, report that boundary; there is no separate tournament tool
or agent CLI fallback.
Require two to four options with benefits, drawbacks, blast radius, durability,
security/data risk, complexity, and verification burden. The options always
include a "do nothing" baseline and a "smallest viable" option alongside the
others, typed as DO_NOTHING and SMALLEST_VIABLE, plus winner and
winnerBeatsDoNothing, task (the original decision task id) and source
(the compared revision). Return one recommended plan, explicit non-goals, and
why the chosen
option beats doing nothing.
For a held specification ambiguity, compare the sidebar research child's technical interpretations and return the recommended one for a REQ correction. Owner-intent choices go to the owner; a tournament does not decide them.
The optional python "<kit-root>/harness/architrave_cli.py" tournament-review
--result <json> --task <id> --source <rev> checks result shape and supplied
bindings only. It cannot authenticate the analyst, verify tradeoffs or authorize
another attempt. Keep the original task's budget and failure identity in the
existing owning host/Run; do not create a separate allowance ledger or reset a
budget by renaming the task. The retired --allowance flag refuses without
writing files. Turn the observed recommendation into one disposition and next
action within existing authority. Automatic cross-successor comparison
accounting remains unqualified.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

