downshift-tune
Skill4 starsChanged 9 days agoApache-2.0View on GitHub
Tune what a session spends in tokens and quota with Downshift installed, in a fixed order with evidence first. Diagnoses routing, fixed context, tool output and project policy, then proposes one change at a time. Use only when the user names Downshift, or asks to cut subagent tokens, context or quota in a project where `downshift doctor` runs. Writes nothing to a file outside the repository without the user's yes.
In this repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- downshift-layeringSkill
- architecture-coverageSkill
- downshift-auditSkill
- downshift-effortSkill
- downshift-orchestratorSkill
- downshift-setupSkill
- downshift-squadSkill
- harness-engineerSkill
- ponytailSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
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
- Distinctive: line 14
Every change to a file outside the repository is shown first and waits for the user's yes.
- Distinctive: line 19
Run all four before proposing anything.
- Very specific: line 28
If Downshift is not routing at all, stop here and hand over to the downshift-setup skill.
- Distinctive: line 34
Fixed context: when the always-loaded set is large or has content for one domain only.
- Distinctive: line 36
Tool output: when sessions re-read long test, build or log output.
- Distinctive: line 38
Project policy: when a low-risk repository keeps spawning at the frontier tier, or a high-risk one keeps rework from downshifts.
- Distinctive: line 40
Misroutes: when a child failed because its tier was too small, or a trivial task kept the frontier tier.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Downshift tune
Downshift does not track spend and does not measure money. It works simply and
model-agnostically: the LLM picks the model, and Downshift only applies the
[tier=small] hint (down only), the limits the user declares (a floor that only
raises, the session allowlist, quota) and reports the result in tokens. This skill
reduces the tokens and quota a session consumes, and the rework a wrong routing
decision causes. Never promise a percentage. Never read or print task prompts.
Every change to a file outside the repository is shown first and waits for the
user's yes.
1. Diagnose, in this order
Run all four before proposing anything. Record what you observed, not what you assume.
| Step | Command | What it tells you |
| Is routing on? | downshift doctor --json | failed checks, each with a fix; companion row says whether a context companion is recorded |
| What did routing do? | downshift stats --days=7 | decisions and held guardrails over the period; frontier rewrites on doubt above 0 is an alarm |
| What loads every session? | wc -c on the always-loaded files (section 3 of the audit skill) plus the skill descriptions and MCP tool schemas | fixed context per session, in bytes (tokens ≈ bytes / 4, say it is an estimate) |
| Where does tool output go? | downshift context status; downshift context metrics | native observe counts; whether a companion compressor is recorded |
If Downshift is not routing at all, stop here and hand over to the downshift-setup skill.
2. Pick the biggest lever
Order by expected effect, then apply one at a time and re-measure:
- Fixed context when the always-loaded set is large or has content for one domain only. references/context-diet.md
- Tool output when sessions re-read long test, build or log output. references/compress-output.md
- Project policy when a low-risk repository keeps spawning at the frontier tier, or a high-risk one keeps rework from downshifts. references/project-policy.md
- Misroutes when a child failed because its tier was too small, or a trivial task kept the frontier tier. references/misroute-triage.md
Routing itself needs no tuning here: it is deterministic and already applied. The LLM
chooses the model; Downshift only carries the [tier=small] hint down and holds the
limits the user declared. Do not teach the user to word prompts so the classifier picks a
smaller tier; that moves risk, not tokens.
3. Report
Table: lever | evidence (command and the line you read) | change proposed | expected effect
(direction only, in tokens, context bytes or quota) | confidence (observed, inferred,
unverified). One change per row. After the user applies one, re-run step 1 next week;
downshift report compares routed and control from their own usage, in tokens per
completed task.
Downshift by Tiago Vilas Boas · https://github.com/tiagovilasboas/downshift-ai
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.