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 big-emotion/agent-atelier --skill bootstrap-confluencegit clone --depth 1 https://github.com/big-emotion/agent-atelierWrote 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/big-emotion/agent-atelier/bootstrap-confluence)<a href="https://agentmods.dev/skills/big-emotion/agent-atelier/bootstrap-confluence"><img src="https://agentmods.dev/badge/skills/big-emotion/agent-atelier/bootstrap-confluence.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 5.1 | $0.00078 | $0.03448 |
| Opus 5 | $0.00039 | $0.01724 |
| Sonnet 5 | $0.00016 | $0.00690 |
| Haiku 4.5 | $0.00008 | $0.00345 |
Grade A, and why
{{project_slug}}-bootstrap-confluence 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 today.
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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{{project_display_name}} Bootstrap Confluence
One-shot creation of the canonical Confluence spec tree (Requirements / Decisions / Architecture / Obsolete) under the project's engineering root page. After publish, the skill writes a sentinel file (docs/.confluence-bootstrap-complete) and refuses to run a second time.
This skill publishes the four pages as skeletons: every REQ/DEC/ARCH section arrives through /{{project_slug}}-spec at status Pending. It is the entry point of the Confluence-as-source-of-truth system, not the ongoing maintenance loop — that belongs to /{{project_slug}}-spec.
When to Activate
- User says: "bootstrap confluence", "initialise l'arbre de spec", "crée l'arbre engineering", "publie l'arbre Requirements/Decisions/Architecture".
- User invokes
/{{project_slug}}-bootstrap-confluence(no arguments). - Activation is forbidden if
docs/.confluence-bootstrap-completealready exists — see Phase 0.
Inputs
None. This skill takes no arguments. Everything it needs is in docs/confluence-spec/config.json.
Preconditions
Verify all of the following before any Confluence write. If any fail, do not modify anything — report the blocker and exit.
- In the repo root —
package.json.nameis{{project_slug}}. If not, stop. - Clean working tree —
git status --porcelainmust be empty. If dirty, stop and ask the user to commit or stash (Phase 5 commits the sentinel + config on a dedicated branch and must not sweep up unrelated changes). - No prior bootstrap sentinel —
docs/.confluence-bootstrap-completemust NOT exist. If it does, read it, print its recorded timestamp + page IDs, and refuse. This skill is one-shot by contract. - Config present and parseable —
docs/confluence-spec/config.jsonmust exist and contain non-nullcloudId,siteUrl,spaceKey,engineeringRootPageId. The four*PageIdfields may benull(fresh config) or hold ids from a previous tree (deliberate re-init) — this skill overwrites them in Phase 4 either way. Do not hardcode these values inside this skill; always read them at runtime. - Atlassian MCP reachable —
mcp__atlassian__getAccessibleAtlassianResourcesreturns the configuredcloudId. Otherwise the publish half is impossible — stop. - No existing spec sub-tree —
mcp__atlassian__getConfluencePageDescendantsonengineeringRootPageIdmust NOT contain a child whose title equals or ends withRequirements,Decisions,Architecture, orObsolete(a prefixed tree uses the{{project_display_name}} — <name>convention — match the suffix, not the exact title). If any exists, refuse and tell the user to remove it manually (or reconcile the config by hand) — a half-built tree is a human decision, not something to merge into silently.
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.
- today First seen · 209 lines · 0 tokens per session scan A 985331d69b68
{{project_slug}}-bootstrap-confluence is a skill published in the GitHub repository big-emotion/agent-atelier (2 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 3,448 once invoked, about $0.0004 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 2026-09-08.
Other skills, from other repositories
confluence
Operational skill for Confluence: spaces, page trees, macros, labels, permissions, and REST content updates.
tpp-orchestrate
Work through a queue of Technical Project Plans serially — delegate each to a TDD subagent, get a cross-model second opinion, empirically vet every finding, and make one coherent commit per plan. Use when executing a documented plan queue such as todo/ or feat-name/ for a port, migration, or multi-stage feature.
tpp
Work on a Technical Project Plan — read the plan, identify the current phase, do that phase's work, and update the plan with discoveries. Use when starting or resuming multi-session work tracked in a plan file.
handoff
Update the active Technical Project Plan for handoff when context is running low or the session is ending, so the next session continues instead of restarting.
github-project-setup
Set up a GitHub Project (v2) for a single repo or a multi-repo platform. Standardized statuses, custom fields (Tier or Initiative + Area/Priority/Effort/Mode), labels, and issue templates. Single-repo flow uses GitHub milestones; multi-repo flow uses a Project Initiative field for cross-repo coordination and surfaces…
to-issues
Break a plan, spec, or PRD into independently-grabbable issues on the GitHub Project using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.