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 pyros-projects/limitless --skill failure-postcardsgit clone --depth 1 https://github.com/pyros-projects/limitlessWrote 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/pyros-projects/limitless/failure-postcards)<a href="https://agentmods.dev/skills/pyros-projects/limitless/failure-postcards"><img src="https://agentmods.dev/badge/skills/pyros-projects/limitless/failure-postcards/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/pyros-projects/limitless/failure-postcards"><img src="https://agentmods.dev/badge/skills/pyros-projects/limitless/failure-postcards.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 | $0.00112 | $0.00717 |
| Opus 5.5 | $0.00045 | $0.00287 |
| Sonnet 5.5 | $0.00022 | $0.00143 |
| Haiku 4.5 | $0.00011 | $0.00072 |
Grade A, and why
failure-postcards 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Failure Postcards
Overview
This skill turns abstract risk into something a builder can feel.
Instead of listing generic failure modes, it writes little artifacts from the future: support emails, bug reports, confused user notes, one-star reviews, postmortem fragments. The point is to make the failure legible fast.
When to Use
Use this when:
- a design sounds good on paper but you do not trust it yet
- the team is discussing risks too abstractly
- you want a pre-mortem without corporate workshop energy
- a key user flow needs pressure-testing from the user's side
Do not use this as theatre. The goal is not to be dramatic. The goal is to expose real fragility.
What to Produce
Generate a small set of future artifacts such as:
- support tickets
- angry or disappointed emails
- confused first-user messages
- one-star reviews
- short postmortem fragments
Then explain:
- what failure each artifact reveals
- what assumption broke
- what design change might prevent it
Working Loop
-
Choose the fragile promise. Pick the feature, flow, or assumption that sounds good but may be hiding a break.
-
Jump forward in time. Imagine the moment after the failure has already happened.
-
Write the artifact from the human side. Let the support email, review, or postmortem fragment reveal what the builder failed to notice.
-
Decode the postcard. Explain the hidden assumption, why it broke, and what design move would reduce the chance of that future.
Suggested Output Shape
PostcardWhat this revealsBroken assumptionWhat to change before this becomes real
Tiny Example
Postcard: "I uploaded the file three times and nothing changed except the spinner. I still don't know if you have it or not."What this reveals: The flow hides system state right when the user most needs reassurance.Broken assumption: The team assumed a spinner counts as feedback.What to change before this becomes real: Show upload progress, success confirmation, and a visible retry state.
What ships with it
2 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 First seen · 91 lines · 112 tokens per session scan A d15532a3306f
failure-postcards is a skill published in the GitHub repository pyros-projects/limitless (2 stars, last pushed yesterday), licensed MIT. It adds 112 tokens to every session and 717 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
monitoring-observability
OpenTelemetry, structured logging, distributed tracing, alerting, and dashboards. Use when instrumenting services, designing logs/traces/metrics, defining SLOs and alerts, or debugging production behavior from telemetry.
debug-systematic
Systematic 4-phase debugging methodology for complex, intermittent, or mysterious issues. Use when investigating bugs, race conditions, or unexplained failures.
thinking-scientific-method
When a symptom has several plausible causes, rank falsifiable hypotheses and run the cheapest discriminating observation first; prefer least-assumptive survivors only after evidence fit.
thinking-five-whys-plus
When a fault is localized and the proximate cause is known but the systemic root is not, chain evidence-linked whys with a counterfactual stop and a countermeasure.
thinking-map-territory
When a claim, doc, test, metric, or assumption conflicts with observed behavior, stop theorizing from the map and verify the live code or data; let territory overrule.
windows-ops
Comprehensive Windows workstation operations - diagnose slow boot, failing drives, BSOD crashes, startup bloat, runaway processes, event logs. Use for: Windows is slow, slow bootup, won't boot, blue screen, BSOD, kernel crash, drive failing, SMART errors, disk errors, Event 41, Event 129, storahci reset, BugCheck…