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 bobberrisford/affiliatemcp --skill reversal-investigationgit clone --depth 1 https://github.com/bobberrisford/affiliatemcpWrote 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/bobberrisford/affiliatemcp/reversal-investigation)<a href="https://agentmods.dev/skills/bobberrisford/affiliatemcp/reversal-investigation"><img src="https://agentmods.dev/badge/skills/bobberrisford/affiliatemcp/reversal-investigation/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/bobberrisford/affiliatemcp/reversal-investigation"><img src="https://agentmods.dev/badge/skills/bobberrisford/affiliatemcp/reversal-investigation.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 | $0.00115 | $0.01389 |
| Opus 5 | $0.00057 | $0.00694 |
| Sonnet 5 | $0.00023 | $0.00278 |
| Haiku 4.5 | $0.00012 | $0.00139 |
Grade A, and why
reversal-investigation 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 12d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Premium scope note
This is net new: the free tier has a reversal/decline report
(programme-reversal-report), but that is advertiser-side, investigating
why a brand's own conversions are being declined. This skill is the
publisher-side mirror: investigating a publisher's own reversed commissions
across the networks they earn from.
This skill is read-only. It surfaces the problem and builds an evidence pack the publisher can send to a network's publisher support team; it cannot approve, reopen, or dispute a transaction. Say so if the user expects an in-tool action.
Assumptions and requirements
- Publisher-side networks only.
- Requires
listTransactionssupport and reversal-reason coverage on the networks in scope; both vary by adapter. CheckknownLimitationsfirst and report any gap rather than guessing. - Credentials for networks in scope are configured; recommend
affiliate-networks-mcp doctor <slug>when credential state is uncertain. - This produces a written case; it does not send it. The publisher decides whether and how to raise it with the network.
Step 1 — identify networks and confirm coverage
Use publisher networks the user named or confirmed configured. Call
affiliate_list_networks to confirm a registered adapter exists per named
network. Check each network's metadata for listTransactions support and
note any gap. Recommend affiliate-networks-mcp doctor <slug> when
credential state is uncertain rather than assuming.
Step 2 — pick the window
Default period: the last 90 days, ending today. Honour an explicit window
("this quarter", "last month", named dates). Compute a same-length prior
window for a trend comparison. Express all dates as ISO YYYY-MM-DD and
state them at the top.
Step 3 — pull reversed and total transactions
For each in-scope network s, call:
affiliate_<s>_list_transactions({ status: "reversed", from, to })
for example affiliate_cj_list_transactions({ status: "reversed", from, to })
or affiliate_awin_list_transactions({ status: "reversed", from, to }). To
compute a reversal rate, also pull the full set for the same window
(affiliate_<s>_list_transactions({ from, to })) and derive the rate as
reversed commission over total commission. If a network does not accept a
status filter, pull the window once and filter reversed rows client-side.
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.
- 12d ago First seen · 126 lines · 115 tokens per session scan A daf0acfe3d3d
reversal-investigation is a skill published in the GitHub repository bobberrisford/affiliatemcp (6 stars, last pushed 1mo ago), licensed MIT. It adds 115 tokens to every session and 1,389 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.
reading-receipt
An image-reading workflow for extracting structured information from receipts, invoices, and hometown-tax donation certificates. It can first extract text from PDFs and otherwise read their images.