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 skills add photostructure/coding-skills --skill tpp-orchestrategit clone --depth 1 https://github.com/photostructure/coding-skillsWrote 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/photostructure/coding-skills/tpp-orchestrate)<a href="https://agentmods.dev/skills/photostructure/coding-skills/tpp-orchestrate"><img src="https://agentmods.dev/badge/skills/photostructure/coding-skills/tpp-orchestrate/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/photostructure/coding-skills/tpp-orchestrate"><img src="https://agentmods.dev/badge/skills/photostructure/coding-skills/tpp-orchestrate.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00075 | $0.01768 |
| Opus 5.5 | $0.00030 | $0.00707 |
| Sonnet 5.5 | $0.00015 | $0.00354 |
| Haiku 4.5 | $0.00007 | $0.00177 |
Grade A, and why
tpp-orchestrate 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 21d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TPP Orchestration
Documented in depth: Claude Code has amnesia. So do PRs, changelogs, and your future self.
You are the orchestrator for a documented queue of Technical Project Plans
(TPPs) — self-contained plan files that carry research, design decisions, and
acceptance criteria across sessions. The queue may be a backlog such as
_todo/ or a temporary feature integration queue such as _feat-auth/; plans
move to _done/ when finished, and a roadmap or queue README.md defines the
order. The TPP system itself — layouts, frontmatter, the plan template — is
defined in the bundled TPP-GUIDE.md, or the project's own
docs/TPP-GUIDE.md, which wins. The sibling tpp and handoff skills work a
single plan within a session; this skill is the loop that drives a whole queue
of them through subagents and review gates.
The loop exists because a subagent's green test suite is not proof of
correctness. ../second-opinion/SKILL.md explains
that failure mode and its counterpart — confidently wrong reviewers — and owns
the gate that settles both. This skill owns the queue around it: delegate,
gate, record, commit, repeat.
User direction
The review gates below are workflow defaults. If the user directs you to commit the current work, follow that instruction without starting or resuming a review, waiting for a reviewer verdict, or asking for approval again, unless the user also requests review first. Use stage to verify and commit the understood scope. Record completed, skipped, and unfinished review work accurately; do not mark unfinished implementation or acceptance criteria done. An instruction about the current commit does not waive reviews for later TPPs. When project instructions require review before every commit, a commit instruction for changes that review has not finished on since they last changed runs the review first, and only an explicit instruction to skip review skips it.
What ships with it
1 file 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.
- 21d ago Changed · +18 lines 854c31882314
- 22d ago Changed · +4 lines eff7ec0b5c4d
- 1mo ago Changed · +1 lines 6b8e04ca415f
- 1mo ago Changed · +11 lines 31a7e0db5a9b
- 1mo ago First seen · 99 lines · 75 tokens per session scan A b8b57a42425a
tpp-orchestrate is a skill published in the GitHub repository photostructure/coding-skills (4 stars, last pushed 21d ago), licensed MIT. It adds 75 tokens to every session and 1,768 once invoked, about $0.0003 per session on Opus 5.5. 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
great_cto
Use when the CTO describes a feature, task, or project goal. Orchestrates the full SDLC pipeline automatically based on project type.
opportunity-solution-tree
Build an Opportunity Solution Tree (OST) to structure product discovery — map a desired outcome to customer opportunities, possible solutions, and experiments. Based on Teresa Torres' Continuous Discovery Habits. Use when the team is unclear what to build next, when multiple opportunities compete, or before writing a…
done-blocked
Reusable reporting contract for any agent that hands work back to the pipeline. Forces ONE of two terminal statuses (DONE or BLOCKED) with a specific evidence shape. Stops vague "probably finished" and "kind of stuck" verdicts.
outcome-roadmap
Transform an output-focused roadmap (feature list) into an outcome-focused one. Rewrites initiatives as outcome statements reflecting user and business impact. Use when a roadmap lists features instead of results, when making a roadmap more strategic, or when communicating what success looks like vs what will be built.
pm-planning
Decomposition methodology for pm agent — turns an approved ARCH document into a Beads task list with explicit dependencies, time-boxes, and acceptance criteria. The pipeline can only orchestrate work it can see; this skill defines what "seeable work" looks like.
github-pr-review
Handles PR review comments and feedback resolution. Use when user wants to resolve PR comments, handle review feedback, fix review comments, address PR review, check review status, respond to reviewer, verify PR readiness, review PR comments, analyze review feedback, evaluate PR comments, assess review suggestions, or…