Skip to content
Back to skills

Downshift Tune

ASecurity

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.

  • 8 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added November 10, 2026
ai-agentsgorailsgit

Works with

  • mcp

Security analysis

A100/100

Pro scans all 5 files and shows the line behind each finding

Scanned November 10, 2026

npx -y skills add tiagovilasboas/downshift --skill downshift-tune --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Downshift Tune?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Downshift Tune
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/tiagovilasboas-downshift-tune/badge)](https://www.skillsdirectory.com/skills/tiagovilasboas-downshift-tune)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: downshift-tune
description: 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.
---

# 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:

1. **Fixed context** when the always-loaded set is large or has content for one domain
   only. [references/context-diet.md](references/context-diet.md)
2. **Tool output** when sessions re-read long test, build or log output.
   [references/compress-output.md](references/compress-output.md)
3. **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](references/project-policy.md)
4. **Misroutes** when a child failed because its tier was too small, or a trivial task kept
   the frontier tier. [references/misroute-triage.md](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

Files in this skill

  • SKILL.md3.4 KB
  • references/compress-output.md1.4 KB
  • references/context-diet.md1.2 KB
  • references/misroute-triage.md1.1 KB
  • references/project-policy.md1.2 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in ai-agents →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.