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/ahepi/deepreason/dr-propose-fixnpx skills add AHepi/DeepReason --skill dr-propose-fixgit clone --depth 1 https://github.com/AHepi/DeepReasonWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ahepi/deepreason/dr-propose-fix)<a href="https://agentmods.dev/skills/ahepi/deepreason/dr-propose-fix"><img src="https://agentmods.dev/badge/skills/ahepi/deepreason/dr-propose-fix.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00036 | $0.00588 |
| Opus 5 | $0.00018 | $0.00294 |
| Sonnet 5 | $0.00007 | $0.00118 |
| Haiku 4.5 | $0.00004 | $0.00059 |
Grade A, and why
dr-propose-fix 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 4d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Propose the fix
Input: DIAGNOSIS.md + REPRO.md. Output: FIX.md. You may read code freely now, but you still change nothing.
Design rules (DeepReason-specific)
- Smallest semantic change that makes the reproduction invert. If a comparison is wrong, fix the comparison — do not redesign the data it compares.
- The record is law. Never change what is WRITTEN to the append-only record to fix what is READ from it. Fix readers (validators, gates, accessors) so old committed roots stay valid. A fix that invalidates existing replay-valid roots is wrong by definition.
- Frozen surfaces need a flag, not a patch. Anything that alters state digests, event application order, manifest schemas, or qualification subjects is out of a normal tranche: FIX.md must say so and stop for operator approval.
- Budgets and priorities are guarantees. A scheduling or budget fix must state the guarantee in one sentence ("the operator's seed question always wins rank ties"; "simulation budgets meter only simulation records") and the fix must make that sentence true in EVERY selection/gate path, not just the default one.
- Counters count one thing. When filtering a pooled collection,
filter by type (
isinstance) at every consumer, and check for the mirror-image bug in the sibling capability before declaring done — note it in PARKED.md if real.
FIX.md template
# Fix: <one line>
Guarantee restored: <one sentence>
Change sites (exhaustive):
- <file:line-range> — <what changes, one line each>
Regression artifact: <the REPRO artifact that must invert, plus
any NEW conditions this fix must be tested against>
Existing tests at risk: <tests whose fixtures assumed the old
behavior, from grep — name them and say whether each will be
updated (fixture was defect-dependent) or must keep passing>
Explicitly not changed: <the tempting neighbor, and why>
Estimated diff: <n> lines across <n> files (must be <=150)
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.
- 4d ago First seen · 59 lines · 36 tokens per session scan A c6d072643232
dr-propose-fix is a skill published in the GitHub repository AHepi/DeepReason (141 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 588 once invoked, about $0.0002 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…