dr-implement-fix

A controlled workflow for applying an approved FIX.md file to DeepReason, including a regression test and the project's full checks. It is the only listed skill allowed to change production code.

In plain words
What is it for?
Use it after a FIX.md approval gate to add the approved code change, its regression test, authorized fixtures, and one commit.
Why use it?
It limits changes to the approved scope and catches defects that return later. The regression test records the evidence behind the fix.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/ahepi/deepreason/dr-implement-fix
Any agent
npx skills add AHepi/DeepReason --skill dr-implement-fix
Clone the repo
git clone --depth 1 https://github.com/AHepi/DeepReason

Made for: Claude Code, Codex.

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,216 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00040 $0.01216
Opus 5 $0.00020 $0.00608
Sonnet 5 $0.00008 $0.00243
Haiku 4.5 $0.00004 $0.00122

Measured 2d ago against content hash 8b0999634efd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dr-implement-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 2d 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.

.claude/skills/dr-implement-fix/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implement the fix

Input: an approved FIX.md. Output: one commit containing the fix, its regression test, and any fixture updates FIX.md authorized — nothing else.

Procedure

  1. Touch only FIX.md's change sites. If implementation reveals a needed site FIX.md missed, STOP: amend FIX.md first (one commit), then continue. Silent scope growth is the failure mode this workflow exists to prevent.

  2. Write the regression test first, converting the REPRO artifact: it fails before your change, passes after. Its docstring names the live run/record that motivated it (e.g. "Regression (selfstudy run-9175f0ec): ..."), so the next reader can find the evidence. Build it to dr-execute-step's "Durable tests, checks, and probes" rules — committed evidence only, meaning over form, mutation-proved, wall-clock scrubbed recursively, absence-tolerant — so it survives repo changes and fails only when the defect returns.

  3. Apply the code change. Comments state the constraint the code cannot show ("compare by handle index, not mapping order: canonical JSON sorts keys"), never the change's history or your reasoning.

  4. Run outward rings, stop at first failure:

     pytest <regression test> -x -q
     pytest <the changed subsystem's test files> -q
     pytest tests/ -q -n 4          # full gate, ~8 min
    

    The full gate must report 0 failed. A pre-existing failure you did not cause: stop, report, do not "fix it while you're there." If FIX.md's change sites touch the packaging surface (pyproject entry points, CLI commands, MCP tools/schema, wheel layout), one more ring the gate does not run: python scripts/wheel_smoke.py, with its pinned expectations updated in this same commit.

  5. A gate failure caused by your change is information: if a fixture depended on the defective behavior (FIX.md predicted it), update the fixture minimally so it exercises what the test actually guards; if the failure is NOT predicted by FIX.md, your fix is wrong — revert to the last green state and return to the orchestrator for re-diagnosis. Never weaken an assertion to green.

  6. If a live run root is needed for the next phase and the identity is occupied: retire it — procedure canonical in dr-drive-harness §3 (retire by rename, commit the rename FIRST as its own commit).

  7. Update the map in THIS commit — see "Map obligations" below.

  8. Before committing, run the mechanized budget gate against FIX.md's Estimated-diff ceiling — the same instrument dr-execute-step uses for Family-2 steps, so this check can no longer be an eyeballed git diff --stat compare:

Read the full file on GitHub · 98 lines

Changes

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.

  1. 2d ago First seen · 98 lines · 40 tokens per session scan A 8b0999634efd

Subscribe to this mod's changes

dr-implement-fix is a skill published in the GitHub repository AHepi/DeepReason (140 stars, last pushed 2d ago), licensed MIT. It adds 40 tokens to every session and 1,216 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

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.

microsoft/vscode · 62 tokens