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 fledgeling-co/fledgeling-plugins --skill armada-syncgit clone --depth 1 https://github.com/fledgeling-co/fledgeling-pluginsWrote 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/fledgeling-co/fledgeling-plugins/armada-sync)<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/armada-sync"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/armada-sync/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/fledgeling-co/fledgeling-plugins/armada-sync"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/armada-sync.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 | $0.00185 | $0.01021 |
| Opus 5.5 | $0.00074 | $0.00408 |
| Sonnet 5.5 | $0.00037 | $0.00204 |
| Haiku 4.5 | $0.00018 | $0.00102 |
Grade A, and why
armada-sync 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 1mo 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Armada Sync — keep the portfolio manifest honest
~/Dev/ARMADA.md is the manifest of record for every active project in ~/Dev. The ship-armada:ship-armada orchestrator plans portfolio-wide work from it, so a stale entry causes bad plans. Your job here is one surgical update: make the entry for the project you just worked in match reality, and stop.
Deliver exactly that scope. Do not refresh other entries, reorganize the manifest, or expand this into a portfolio survey — those belong to ship-armada:ship-armada.
Running as a Gemini model? Read gemini.md in this directory first, then follow this file with the overrides it names. It replaces step 4's six-edits-in-one-rewrite with four passes over a manifest too large to Read whole, and turns the entry's caps — 20 lines, 8 features, 3 opportunities, one changelog line, one entry — into a snapshot diff that reads each one back. Other models skip it.
Protocol
- Identify the project. It is the
~/Dev/<project>directory you are working in (walk up from cwd to the child of~/Dev). If you are in~/Devitself, ask which project to sync rather than guessing. - Read the current entry. Open
~/Dev/ARMADA.md, find the### <project>section and its row in the index table. If the manifest does not exist, say so and suggest runningship-armada:ship-armada(survey mode) to create it; do not scaffold a one-project manifest. - Gather the delta cheaply.
git -C ~/Dev/<project> log --oneline --since=<entry's updated stamp>plus what you already know from the session. Only open docs (README, CLAUDE.md, specs/plans dirs, mocks) whose references you have reason to believe changed. - Rewrite the entry in place, keeping the template shape below and the entry under ~20 lines. Update: the
updated:stamp (today, YYYY-MM-DD), Status (1–2 sentences of current truth), Features (add/adjust; keep the list ≤8, most important first), Read more paths (specs/plans counts, new ORCHESTRATOR.md, newest mocks — verify each path you write exists), and AI/tech opportunities if the work closed or created one. - Update the index row (same status phrase, same date) and append one line to the
## Changelogsection:- 2026-08-07 <project>: <what changed in one clause>. - Report in one or two sentences what you changed in the entry.
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.
- 1mo ago Changed 1aead0cd0ec1
- 1mo ago First seen · 39 lines · 185 tokens per session scan A 92f6cddb5351
armada-sync is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 4d ago), licensed MIT. It adds 185 tokens to every session and 1,021 once invoked, about $0.0007 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 2026-09-04.
Other skills, from other repositories
story-readiness
Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…