Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/rakovi4/continue-framework/retiernpx skills add rakovi4/continue-framework --skill retiergit clone --depth 1 https://github.com/rakovi4/continue-frameworkWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00052 | $0.02832 |
| Opus 5 | $0.00026 | $0.01416 |
| Sonnet 5 | $0.00010 | $0.00566 |
| Haiku 4.5 | $0.00005 | $0.00283 |
Grade A, and why
retier scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/retier — One-Shot Tiering Migration
A scenario's tier lives in its Tier: marker inside the story's tests/*.md
(.claude/templates/spec/tier-ladder.md). /retier writes those markers for stories
drafted before tiering existed whose implementation has not started — why that
needs a migration at all, and why a story already under way is left alone, is in
.claude/guidelines/workflow-detail.md, "Bootstrapping".
Run it once, after the merge. /framework-sync's Next Steps routes here when
the merge brings tiering in; the frontmatter description above repeats the run-once
instruction for a hand-merge that never invoked that skill. Afterwards /test-spec
Phase 5 tiers every new story and nothing calls this skill again.
Run it inline in the main agent. It fans out one tiering-agent per story, and
those must not nest inside a wrapper agent. It is never a progress.md checkbox, so
/continue has no dispatch row for it. Stories only — a task has no scenario
set and is never tiered.
Scope by story state
Classify every folder under ProductSpecification/stories/ first, then act.
Never descend into ProductSpecification/stories/done/, and never classify done/
itself as a story folder. This is the one deliberate exception to resolving both
locations (.claude/rules/workflow.md, "Resolving a story folder"): everything in the
archive is complete, which is already the Skip row below — reaching it by walking the
archive would only re-derive that answer, while treating done/ as a story would put a
non-story on the classification path at all.
Test the rows in order; the first match wins — a Done story's tests/ exist and
its checkboxes are [x], so it matches the last two rows too, and only row order
keeps it out of them.
| State | Detected by | Action |
|---|---|---|
| Not specced | no tests/ directory |
Nothing. /test-spec tiers it when it runs. |
| Done | row in the Done table of ProductSpecification/stories.md |
Skip, and say so in the report. |
| Already tier-major | progress.md has a ## Tier N — section |
Nothing — specced after the merge, or migrated by an earlier run. |
| Convertible | tests/ exist, no checkbox below the ## Spec section is [x] |
Tier the set, then re-bootstrap progress.md tier-major. |
| In flight | tests/ exist, at least one checkbox below ## Spec is [x] |
Nothing. Left untiered permanently. |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 187 lines · 52 tokens per session scan A b60b66126ec5
retier is a skill published in the GitHub repository rakovi4/continue-framework (50 stars, last pushed 6d ago), licensed MIT. It adds 52 tokens to every session and 2,832 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…