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 follow-throughgit 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/follow-through)<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/follow-through"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/follow-through/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/follow-through"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/follow-through.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 | $0.00058 | $0.00634 |
| Opus 5.5 | $0.00023 | $0.00254 |
| Sonnet 5.5 | $0.00012 | $0.00127 |
| Haiku 4.5 | $0.00006 | $0.00063 |
Grade A, and why
follow-through 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 5d 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.
What it actually says
Follow through
Turn the requested loose ends into a short account of what is known, what changed, and what can be done next. Keep the original request, time window and completion condition: a review of yesterday's activity is not permission to manage the whole inbox or start recurring work.
| Requested outcome | Skill |
|---|---|
| Errors, billing notices, cloud credits, operational inbox | follow-through:ops-triage |
| Parcels, returns, appointments, household administration | follow-through:household-follow-up |
| A choice supported by product or tool research | follow-through:decision-brief |
| Promises, dependencies and handoffs with colleagues | follow-through:commitments |
| Existing agents or a release session need continuation | flagship:fleet-console |
| Repeatable navigation, keyboard, theme and width checks | test-campaign:ui-regression |
Read references/evidence-contract.md before collecting sources or writing a ledger. Domain skills use the same contract; load only the domain needed. Verify a referral is installed in the receiving runtime. If it is absent, report the missing dependency and complete the bounded read-only portion directly with this contract; do not claim the referral ran.
For a mixed request, keep one local ledger with domain-labelled items and one summary, rather than four independent lists that repeat the same thread. An alert about a delivery can belong to the household domain while retaining its email source. Do not dispatch domain agents automatically.
The optional deterministic helper checks source links, duplicate identities, freshness and completion claims, then prints the actionable and unresolved rows:
python3 <plugin-root>/scripts/ledger.py check <ledger.json>
python3 <plugin-root>/scripts/ledger.py summary <ledger.json>
Use references/ledger-format.md when retaining state between runs. For a small one-off request a concise cited table is enough. Store working evidence outside this reusable plugin, in the task's permitted private workspace. No accounts, personal history or messages belong in plugin examples.
For the design basis and limits of the evidence checks, see references/evidence.md.
Stop when the requested set has been reconciled and each row has either a proven outcome, a next action, or a named blocker. If authorised execution is part of the request, carry it through to the agreed outcome and verify it. A draft, scheduled task, accepted handoff and completed outcome are different states. For future work, use the runtime's supported scheduling tools only when the user asked for it; check required connector access and existing schedules first.
What ships with it
4 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.
- 5d ago First seen · 56 lines · 58 tokens per session scan A c02f2ee84a12
follow-through is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 4d ago), licensed MIT. It adds 58 tokens to every session and 634 once invoked, about $0.0002 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 2026-10-12.
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…