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 CodedRichy/food-chain-ideation --skill food-chain-monitorgit clone --depth 1 https://github.com/CodedRichy/food-chain-ideationWrote 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/codedrichy/food-chain-ideation/food-chain-monitor)<a href="https://agentmods.dev/skills/codedrichy/food-chain-ideation/food-chain-monitor"><img src="https://agentmods.dev/badge/skills/codedrichy/food-chain-ideation/food-chain-monitor/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/codedrichy/food-chain-ideation/food-chain-monitor"><img src="https://agentmods.dev/badge/skills/codedrichy/food-chain-ideation/food-chain-monitor.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 | $0.00076 | $0.01615 |
| Opus 5 | $0.00038 | $0.00807 |
| Sonnet 5 | $0.00015 | $0.00323 |
| Haiku 4.5 | $0.00008 | $0.00161 |
Grade A, and why
food-chain-monitor 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Food Chain Monitor
What This Is
A delta battle — the ongoing health-check companion to food-chain-ideation. Run it after pivots, after major feature additions, after market changes. It tests ONLY what changed since the last battle. Everything that already survived stays untouched.
What This Is NOT
- Not a full food chain battle. That is
food-chain-ideation. If you want to stress-test an idea from scratch, go there. - Not a replacement for the Battle Log. This skill REQUIRES a prior Battle Log. If the user does not have one, redirect them: "You need to run food-chain-ideation first to establish a baseline Battle Log. I can't monitor changes to something that hasn't been battle-tested yet."
Input Requirements
| Input | Required | Description |
|---|---|---|
| Battle Log | YES | From a prior food-chain-ideation session. Contains the original idea, evolved idea, apex predator, patches, and UAS. |
| What Changed | YES | A plain-language description: "we pivoted from X to Y", "we added feature Z", "competitor launched W", "market shifted because of Q". |
| Action Log | NO | From apex-to-action. If provided, the monitor checks whether executed actions are still valid post-change. |
If the user provides no Battle Log, do NOT proceed. Redirect to food-chain-ideation.
Step 1 — Delta Analysis
Identify exactly what is new. Do not re-litigate settled assumptions.
## Delta Analysis
| Field | Value |
|---|---|
| **Prior battle** | [date, original idea, evolved idea from battle log] |
| **What changed** | [user's description, quoted verbatim] |
### New Assumptions Introduced
| # | Assumption | Why New |
|---|---|---|
| 1 | [assumption] | [why this is new] |
| 2 | [assumption] | [why this is new] |
| ... | [max 5 — pick the 5 most vulnerable] | ... |
### Prior Patches
| Patch | Status |
|---|---|
| [patch from battle log] | STILL VALID / NEEDS RE-EVALUATION |
| ... | ... |
**Prior apex predator:** [animal from battle log] — still relevant? [YES / NO + one sentence why]
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 · 166 lines · 76 tokens per session scan A 90b0fef93c9d
food-chain-monitor is a skill published in the GitHub repository CodedRichy/food-chain-ideation (3 stars, last pushed 3d ago), licensed MIT. It adds 76 tokens to every session and 1,615 once invoked, about $0.0004 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
research-brief-creator
Produces a structured research brief for a reporter starting a new story assignment — covering the key questions to answer, the types of sources to seek, documents to obtain, and potential story angles to investigate.
story-angle-finder
Generates 6–8 distinct editorial angles from a broad topic or news event, each with a unique perspective, target audience, and reporting approach.
episode-concept-generator
Generates 6–8 fully developed episode concepts aligned to a podcast's format, theme, and audience — each with a title, premise, guest or source approach, and core listener question.
headline-generator
Generates a range of headline and subheadline options across different registers, lengths, and publication styles for a given article or feature.
creative-sparring
A structured creative partner for exploring and stress-testing ideas for products, features, or tools.
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…