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/kkollsga/codingest/phased-plannpx skills add kkollsga/codingest --skill phased-plangit clone --depth 1 https://github.com/kkollsga/codingestWrote 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/kkollsga/codingest/phased-plan)<a href="https://agentmods.dev/skills/kkollsga/codingest/phased-plan"><img src="https://agentmods.dev/badge/skills/kkollsga/codingest/phased-plan.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 | $0.00100 | $0.05933 |
| Opus 5 | $0.00050 | $0.02967 |
| Sonnet 5 | $0.00020 | $0.01187 |
| Haiku 4.5 | $0.00010 | $0.00593 |
Grade A, and why
phased-plan 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 — 363 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phased plan
For any large feature or non-trivial refactor of codingest. Demand this
skill when the user kicks off such work. Do not use standard plan mode
(EnterPlanMode / ExitPlanMode) — this skill builds its own gated phased
plan instead of the harness's generic plan.
Working dir: dev-docs/ (gitignored)
All plans, scratch, and intermediates live under dev-docs/ — gitignored
local working state. The canonical layout + lifecycle is dev-docs/README.md
— read it; it's the source of truth, this is just the phased-plan-relevant
subset:
- This project's plan →
dev-docs/plans/<slug>.md(durable). - Design choices/trade-offs you weigh (parity/sync/algorithm) →
dev-docs/designs/(durable). - Open threads → a lean one-line backlink in
dev-docs/todos.md(detail in the linked durable doc, never inline). - Offload large output to
dev-docs/temp/and report the path (>1-day purge) instead of printing it — stays under the response token gate. - Parity/perf: harnesses →
bench/scripts/, regression rows →bench/results/results.csv, heavy built graphs/dumps →bench/out/(>14-day purge; never write artifacts next to the script). The committed regression record isPARITY.md+tests/parity.rsandBENCHMARKS.md.
Doctrine sync — first action of the run, before Phase −1
The estate's rules live in the sibling doctrine repo and are versioned. Pull
them forward before planning anything, so a plan is never built on doctrine
this repo has already been told is superseded.
- Read
../doctrine/VERSION(a date serial, e.g.2026.08.10) anddev-docs/.doctrine-synced. If the marker is absent, create it with the current version and note in the report-out that this was a first sync (there is nothing to replay — the marker's job starts now). - Versions equal → done. That is the normal case and it costs one file read; it is never worth skipping to save time, and "we're probably current" is not the check.
- Doctrine ahead → read
../doctrine/CHANGELOG.mdforward from the marker and act on every entry newer than it. Each item carries exactly one action class:[skills-update]— merge the change into this repo's declared authority (per the Authority line at the top of AGENTS.md: the conventions file itself, and the tracked.agents/skills/tree) and regenerate the adapters from it in the same action. Never hand-port into an adapter — that is what doctrineR7measures.[local-sweep]— run the check command the entry states. If it comes back clean, say so and move on. If it fails, the sweep becomes Phase 0 work of this plan — scoped, listed, and visible in the plan doc — never a silent side-task folded into an unrelated phase.[info]— nothing to do.
- Write the new version to
dev-docs/.doctrine-syncedonly after those actions completed. A marker written first permanently hides the entry it skipped: the next run compares against it and sees nothing. If an entry could not be actioned, the marker advances only once that item is in the plan — the plan is the record, not the marker.
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 · 363 lines · 100 tokens per session scan A 3e7c044256a0
phased-plan is a skill published in the GitHub repository kkollsga/codingest (0 stars, last pushed yesterday), licensed MIT. It adds 100 tokens to every session and 5,933 once invoked, about $0.0005 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…