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/curtisthe/three-pillars-plugin/tp-docs-updatenpx skills add CurtisThe/three-pillars-plugin --skill tp-docs-updategit clone --depth 1 https://github.com/CurtisThe/three-pillars-pluginWrote 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/curtisthe/three-pillars-plugin/tp-docs-update)<a href="https://agentmods.dev/skills/curtisthe/three-pillars-plugin/tp-docs-update"><img src="https://agentmods.dev/badge/skills/curtisthe/three-pillars-plugin/tp-docs-update.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 | $0.00039 | $0.01281 |
| Opus 5 | $0.00019 | $0.00641 |
| Sonnet 5 | $0.00008 | $0.00256 |
| Haiku 4.5 | $0.00004 | $0.00128 |
Grade A, and why
tp-docs-update 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docs Update
Propose targeted updates to one or more of the four project docs based on recent work.
Argument: [vision|architecture|roadmap|known-issues] (optional) — update a specific doc. If omitted, reviews all four.
Prerequisites
- At least one of the four docs must exist in
three-pillars-docs/. If none exist, suggest running/tp-setup(for vision) or/tp-docs-init(for the other three) first and stop.
Steps
-
Run first-run preflight per skills/_shared/first-run.md.
-
Validate argument if provided — must be one of
vision,architecture,roadmap,known-issues. Reject unknown values. -
Determine which docs to update: use the argument, or default to all four that exist.
-
For each doc, read the current content and gather recent context:
- Completed designs in
three-pillars-docs/completed-tp-designs/(read design.md for scope) - Active spike results in
three-pillars-docs/tp-designs/*/spike-results.md - Recent git log (last 20 commits) for changes since doc was last updated
- Any
implementation-audit.mdorreview.mdfiles with findings
- Completed designs in
-
Vision update protocol (vision only): Updating
three-pillars-docs/vision.mdis a higher-stakes edit than the other docs because every downstream TDD skill reads it. Do not propose vision edits automatically from git log or completed designs — a stream of shipped features is not a signal that the why changed. Only propose vision edits when:- Recent spike results explicitly concluded the vision needs updating (check
spike-results.mdfor vision callouts) - An audit surfaced a MISALIGNMENT finding that the user resolved by deciding the vision was wrong rather than the design
- The user explicitly invokes
/tp-docs-update visionto reconsider the why When proposing vision edits, reopen the Part A conversation from/tp-setupfor the affected sections rather than silently rewriting — the user should answer the questions again, not rubber-stamp a diff. Flag downstream impact: list designs whose Vision alignment section would need to be re-checked against the new vision.
- Recent spike results explicitly concluded the vision needs updating (check
-
Review Current Focus (roadmap only): If updating the roadmap and it has a
## Current Focustable, check for staleness — items marked done in Design Inventory but still in Current Focus, blockers that have been resolved, next actions that are outdated. Propose corrections as part of the roadmap edits. -
Propose specific edits as diff-style before/after blocks:
- Show the current text that would change
- Show the proposed replacement
- Explain why this update is needed Process one doc at a time so the user can approve/reject granularly.
-
On user confirmation, write the changes and follow
skills/_shared/living-doc-format.md:- Update the
*Last updated: YYYY-MM-DD*marker on line 2–3 of the doc to today's date. - Append one dated line at the top of the
## Historysection (newest-first):- YYYY-MM-DD — one-sentence summary.Keep it under 800 non-ws chars. Do not expand the*Last updated:*line with a prose summary — the summary goes in## History.
- Update the
-
Commit the doc updates per
skills/_shared/commit-after-work.md. Artifact paths to stage: only the doc files actually modified in step 7 — any ofthree-pillars-docs/vision.md,three-pillars-docs/architecture.md,three-pillars-docs/product_roadmap.md,three-pillars-docs/known_issues.md,three-pillars-docs/known_issues_resolved.md(when an update resolves an issue, move its entry verbatim to the resolved archive — never mark it resolved in place).
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 · 55 lines · 39 tokens per session scan A b162f22d0655
tp-docs-update is a skill published in the GitHub repository CurtisThe/three-pillars-plugin (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 39 tokens to every session and 1,281 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…