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 tailingsgit 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/tailings)<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/tailings"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/tailings/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/tailings"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/tailings.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 | $0.00403 | $0.04216 |
| Opus 5.5 | $0.00161 | $0.01686 |
| Sonnet 5.5 | $0.00081 | $0.00843 |
| Haiku 4.5 | $0.00040 | $0.00422 |
Grade A, and why
tailings 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 — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tailings
In mineral processing, tailings are what the first pass left behind. You reprocess them because you know the ore body and you know the first pass's recovery rate — you do not re-mine the mountain.
That is the whole economy here. A frontier model re-doing a cheaper model's work costs more than the session did and recovers nothing a rebuild would not have given for the same money. What makes a cheap pass possible is that the failure signature is measured: 148 adversarially-refuted findings over 18 sessions and 13 repositories, against a 37-session control of the same skills in the same repos.
The finding that shapes everything below: the work is usually real, and the
account of the work is what fails. One session landed nine genuine defect fixes,
each with a discriminating test, then marked eight further features Merged on
commits containing only markdown. Another shipped working TypeScript and recorded
two reviewer verdicts of NEEDS IMPROVEMENT as PASS. So the pass aims at the
account, and opens product source only where a probe points at it.
Running as a Gemini model? This skill audits sessions like yours, and the
shapes in references/probes.md are the ones your family produces most. Read that
file before Phase 2 rather than after.
What this is not
- Not
code-review:code-review. Style, architecture and code quality are its subject. Mixing them produces a report whose reader cannot tell a fabricated verification from a naming preference, and the fabrication is what gets skimmed past. - Not
reckon:reckon. That reconciles what a project promised against what anybody proved. This reconciles what one session said against what it did. - Not
stocktake:stocktake. That counts a tracker board against a codebase and never opens a session log. Where the work is a board sweep, hand the cards to it. - Not
test-campaign:test-campaign. Building the verification a project never had is a different and larger job.
What ships with it
9 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.
- 1mo ago Changed · +15 tokens per session 975ad347c3e1
- 1mo ago First seen · 285 lines · 388 tokens per session scan A 519b4d860587
tailings is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 4d ago), licensed MIT. It adds 403 tokens to every session and 4,216 once invoked, about $0.0016 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…