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/a1f/agent-templates/course-correctnpx skills add a1f/agent-templates --skill course-correctgit clone --depth 1 https://github.com/a1f/agent-templatesWrote 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/a1f/agent-templates/course-correct)<a href="https://agentmods.dev/skills/a1f/agent-templates/course-correct"><img src="https://agentmods.dev/badge/skills/a1f/agent-templates/course-correct.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 | $0.00038 | $0.02741 |
| Opus 5 | $0.00019 | $0.01371 |
| Sonnet 5 | $0.00008 | $0.00548 |
| Haiku 4.5 | $0.00004 | $0.00274 |
Grade A, and why
course-correct 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Course Correct
Step back from a PRD issue mid-build and ask what per-PR review can't: does the merged work plus the remaining plan still reach the goal — and if not, what to add, remove, or re-scope?
Judges the plan, not the code — reviewer and critic own quality; this
never writes code or PRs, only edits the plan in place, behind a gate.
Checkpoint-aware — each run digests only what merged since the last; re-run it
each time a wave of PRs lands.
/course-correct [--issue=N] [--since=<git-ref>]
1. Find the issue; read goal + plan + the checkpoint
2. Gather what landed since the checkpoint (merged PRs + diffs)
3. Read the merged diffs against the goal (read-only subagents)
4. Judge drift; draft a Status refresh + plan edits
5. Discuss and approve (gate)
6. Apply to the SAME issue; post an audit comment; advance the checkpoint
Phase 1 — Find the issue and read the checkpoint
Use --issue=N if given; else scan the conversation for the last
PRD published: ... (issue #N) line, or ask. Confirm an auto-detected number.
The body must have ## Build plan and ## PR breakdown — if either is
missing, stop and run /to-issues then /pr-breakdown first.
Read, and keep separate:
-
The goal — the PRD prose (The problem / What we're building / decisions / scope). Re-read it fresh each run — it's the yardstick; if the goal itself was rewritten, re-judge the whole plan against the new one.
-
The plan — the
## Build planslices and## PR breakdownrows. -
The checkpoint — the marker left in the Status block:
<!-- course-correct baseline=<sha> checked=<iso-date> -->baselineis the commit last reconciled. Resolve it intoBASELINE, in order:--since=<ref>, if given.- the marker's
baseline=<sha>, if still in history (git cat-file -e "<sha>^{commit}"succeeds). - otherwise — first run, missing marker, or a force-pushed sha — reconcile the whole build from the parent of its earliest merged PR:
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 · 221 lines · 38 tokens per session scan A ee07138b1849
course-correct is a skill published in the GitHub repository a1f/agent-templates (2 stars, last pushed 3d ago), licensed MIT. It adds 38 tokens to every session and 2,741 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 2026-08-31.
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…