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 kalyvask/winning-writing --skill graveyard-historiangit clone --depth 1 https://github.com/kalyvask/winning-writingWrote 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/kalyvask/winning-writing/graveyard-historian)<a href="https://agentmods.dev/skills/kalyvask/winning-writing/graveyard-historian"><img src="https://agentmods.dev/badge/skills/kalyvask/winning-writing/graveyard-historian/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/kalyvask/winning-writing/graveyard-historian"><img src="https://agentmods.dev/badge/skills/kalyvask/winning-writing/graveyard-historian.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00138 | $0.01670 |
| Opus 5 | $0.00069 | $0.00835 |
| Sonnet 5 | $0.00028 | $0.00334 |
| Haiku 4.5 | $0.00014 | $0.00167 |
Grade A, and why
graveyard-historian 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Graveyard historian
Source: the Konrad/Hertzberg "do your homework" rule taken seriously, applied to the entire industry's history and not just the recipient.
The premise
Most pitches read as if the idea is unprecedented. It almost never is. Someone tried it in 2014 and ran out of runway. Someone else tried it in 2019 and got acquired into irrelevance. A third tried it in 2022 and pivoted away from the original thesis.
A pitcher who can name the graveyard, explain why each previous attempt died, and identify who survived to tell the tale signals three things at once:
- You did the work. You aren't reinventing dead startups by accident.
- You have a falsifiable thesis about why this time is different — grounded in specific failure modes, not vibes.
- You know who to call. The operators who lived through the failures are the most valuable advisors any investor can introduce you to.
Investors love this move because it inverts the asymmetry — the pitcher usually knows less industry history than the investor, and showing up with a graveyard reverses that.
The output of this skill
Two artifacts:
1. The graveyard table — added to the user's about-me / pitch context so Coach can use it in dossiers and openers.
2. A people-to-talk-to list — operators and investors who lived through specific failures. These become candidate warm-intro targets, advisors, or just inputs to the user's own thinking.
How to run
Step 1 — Define the pitch one sentence wide
Have the user state the idea as: "I'm building [X] for [audience] that solves [problem]." If the user can't compress it, run pitch-coach first.
Step 2 — Search the graveyard
Use web_search (if available) and your training data to find companies that tried a substantively similar thing in the last 5–25 years.
For each one, capture:
| Field | Detail |
|---|---|
| Company | Name + (founders) + (years active) |
| Funding | Total raised, lead investors |
| Specific approach | One sentence on what they actually built |
| Outcome | Shut down / acquihire / pivoted / zombie |
| Why they died | The specific failure mode, not the generic "no PMF" |
| Lessons | One or two transferable lessons for the user's pitch |
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 · 134 lines · 138 tokens per session scan A 0eccb7b4580f
graveyard-historian is a skill published in the GitHub repository kalyvask/winning-writing (14 stars, last pushed 6d ago), licensed MIT. It adds 138 tokens to every session and 1,670 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
project-memory
Generate a project-specific context file from a brief so an AI assistant remembers your editorial constraints, voice, audience, and quality bar across sessions.
project-retrospective
Generate a LESSONS.md from a finished project: what worked, what didn't, what to reuse, what to retire — formatted for next-project carry-over.
template-selector
Recommend the right skill bundle, agent, and workflow sequence for a new project — so media professionals can start producing instead of browsing a 394-skill library.
multi-author-harmonizer
Reviews a text written or assembled by multiple authors and produces a detailed inconsistency report — flagging voice shifts, terminology mismatches, tonal clashes, and formatting discrepancies — with specific harmonisation recommendations for each.
version-comparator
Compares two versions of an article and produces a structured change report — highlighting substantive edits, additions, deletions, and tone shifts — so the editor or writer can quickly understand what changed and assess whether the revisions improved the piece.
jargon-flagger
Scans a draft and flags every instance of technical jargon, unexplained acronyms, and insider language that a general-audience reader would not understand — with a plain-language alternative for each.