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.
git 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/plugins/fledgeling-co/fledgeling-plugins/stocktake)<a href="https://agentmods.dev/plugins/fledgeling-co/fledgeling-plugins/stocktake"><img src="https://agentmods.dev/badge/plugins/fledgeling-co/fledgeling-plugins/stocktake.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
stocktake 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 3d 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 — 10 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "stocktake",
"description": "Count what a tracker board claims against what the codebase actually holds, card by card, and move each one to the column its evidence supports. Reads every comment and attached image and rebuilds the numbered requirement list from the ticket BEFORE opening any completion record or diff, because a diff read first supplies the frame and the requirements it silently dropped never enter the list. Locates the work \u2014 merged, on a branch nobody merged, unpushed, in a worktree, or never built \u2014 then traces each requirement to the code that PRODUCES its value rather than to a surface that renders it, and judges whether the tests standing behind it could actually fail: which rung of oracle each critical requirement stands on, armed and unarmed assertions counted apart, a denominator for what the gate really runs. Grades every verdict out of family with a single strongest judge rather than a panel, because nine frontier judges across seven families supply about two independent votes. An inconclusive result blocks and never rounds up to a pass. Cards with work left get a brief written for ship-fleet to orchestrate; cards with open decisions get referred to another model family or decided with a named recommendation rather than parked on the reader; cards whose evidence holds are promoted to Done \u2014 and never past it into a human's column until eight named preconditions hold for one pre-registered low-risk class, which a bundled gate refuses by default. Use whenever someone asks to triage, sweep, review, reconcile or clean up a board or backlog, asks what is left across a set of tickets, asks whether items in a review column are genuinely done, asks which tickets sit in the wrong status, or says a column has piled up. At Done, the column a card may reach is decided by the `warrant` plugin rather than by a checklist: warrant_column.py reads the signed warrant and the ratchet's last word and returns Verified where the card'What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 278 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 3d ago First seen · 10 lines scan A 9bc8e077814d
stocktake is a plugin published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
review-suite
Independent plan and delivery reviews with evidence-based verdicts.
nid-team
NI&D team PR triage and review workflow tools.
draft
Context-Driven Development: draft specs and plans before implementation. Structured workflows for features and fixes.
lets
Development workflow with session management, code review, and task tracking.
pm
GitHub issue lifecycle: brainstorm design approaches, create structured issues for LLM agent teams, triage and recommend next issues, audit and clean up stale backlogs, and deep-validate individual issues against the codebase.
rook-maintainer
Maintainer-grade skills for rook (github.com/rook/): code review, backlog triage, systemic-PR campaigns, and the rook house conventions they enforce.