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/photostructure/coding-skills/tppnpx skills add photostructure/coding-skills --skill tppgit clone --depth 1 https://github.com/photostructure/coding-skillsWhat 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 | $0.00047 | $0.00580 |
| Opus 5 | $0.00023 | $0.00290 |
| Sonnet 5 | $0.00009 | $0.00116 |
| Haiku 4.5 | $0.00005 | $0.00058 |
Grade A, and why
tpp 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.
How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work on TPP
Documented in depth: Claude Code has amnesia. So do PRs, changelogs, and your future self.
A Technical Project Plan (TPP) is a living handoff document: it carries research, design decisions, failed approaches, and next steps across sessions, so the next session (or the next engineer) continues instead of restarting.
Make progress on the referenced TPP. Determine the current phase and take appropriate action.
Required Reading First
Before any work, you MUST read:
- The project's instructions:
AGENTS.md, plusCLAUDE.mdwhen present - The project's TPP guide:
docs/TPP-GUIDE.mdif it exists; otherwise the bundled reference TPP-GUIDE.md
Process
- Read the referenced TPP. It will live in
_todo/, in a priority folder (_active/,_p1/…_p4/), or in a documented feature integration queue matching_feat-<name>/if this project uses them. - Identify the current phase.
- Do the work for that phase.
- Update the TPP with progress and discoveries — gotchas, rejected approaches, and the why behind decisions, not a transcript.
When context runs low before the work is done, invoke the handoff skill rather than
letting the session end silently. When the TPP is complete, move it to _done/.
Adapting for your project
- Create a project
docs/TPP-GUIDE.md(start from the bundled reference) and tailor the layout, frontmatter fields, and template to your conventions — the project guide always takes precedence over the bundled copy. - Extend the required reading list with your high-value docs
(
DESIGN-PRINCIPLES.md,TDD.md, architecture decisions). Every listed file is read on every invocation, so keep it short. - Automate durable reminders portably. Put the TPP update requirement in
the repository's
AGENTS.md, or use a supported project hook or automation that prompts the coding agent to update the active TPP before a task ends.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 51 lines · 47 tokens per session scan A a8a588207584
tpp is a skill published in the GitHub repository photostructure/coding-skills (3 stars, last pushed 2d ago), licensed MIT. It adds 47 tokens to every session and 580 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
agile-product-owner
../../../product-team/agile-product-owner/skills/agile-product-owner/SKILL.md.
atlassian-templates
../../../project-management/skills/atlassian-templates/SKILL.md.
atlassian-admin
../../../project-management/skills/atlassian-admin/SKILL.md.
board-meeting
../../../c-level-advisor/skills/board-meeting/SKILL.md.
add-azuredevops
Adds Azure DevOps connector to a Power Apps code app. Use when querying work items, creating bugs, managing pipelines, or making ADO API calls.
37signals-way
Build lean, opinionated products using the 37signals philosophy from "Getting Real", "Rework", and "Shape Up". Use when the user mentions "Getting Real", "Rework", "Shape Up", "37signals", "Basecamp method", "six-week cycles", "fixed time variable scope", "appetite vs estimates", "betting table", "breadboarding", "fat…