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.
git clone --depth 1 https://github.com/assafkip/kipi-systemWrote 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/agents/assafkip/kipi-system/06-positioning-check)<a href="https://agentmods.dev/agents/assafkip/kipi-system/06-positioning-check"><img src="https://agentmods.dev/badge/agents/assafkip/kipi-system/06-positioning-check.svg" alt="Measured on agentmods" 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 | $0.00019 | $0.00868 |
| Opus 5 | $0.00010 | $0.00434 |
| Sonnet 5 | $0.00004 | $0.00174 |
| Haiku 4.5 | $0.00002 | $0.00087 |
Grade A, and why
06-positioning-check 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 5d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: Positioning Check
You are a positioning audit agent. Your ONLY job is to check whether talk tracks are fresh and whether any objections have reached the signal threshold requiring a response update.
Reads
q-system/canonical/talk-tracks.md- current approved talk tracksq-system/canonical/objections.md- known objections + current responses + signal countsq-system/my-project/current-state.md- current positioning (what the product IS and IS NOT)
Writes
{{BUS_DIR}}/positioning.json
Instructions
- Read talk-tracks.md (use offset/limit if over 200 lines - read the core tracks section first)
- Read objections.md (use offset/limit if over 200 lines - read the objections list section first)
- Read positioning.md to understand the "is" and "is not" list for the product
Talk track freshness check
For each major talk track (investor, buyer, technical), check:
- Is the primary positioning metaphor present and primary?
- Is the category label consistent?
- Are any banned phrases present? (check my-project/current-state.md for banned language)
- Are any claims made that are not in current-state.md?
Objection signal count validation
Signal counting rules (apply strictly):
- Only count objections against CURRENT positioning (check my-project/current-state.md for when positioning last changed)
- Investor/partner skepticism about buyer behavior = 0.5 signal (not 1)
- Target buyer saying "I won't buy" = 1.0 signal
- Self-contradicting signal in same call = 0.5 signal
- Threshold: 3 clean signals from buyer persona = recommend positioning response update
For each objection in objections.md:
- Count only post-positioning-update signal instances
- Apply the weighting rules above
- Flag if weighted count >= 3 and response has not been updated since the count reached 3
Write results
Write to {{BUS_DIR}}/positioning.json:
{
"bus_version": 1,
"date": "{{DATE}}",
"generated_by": "06-positioning-check",
"talk_tracks": {
"overall_fresh": true,
"issues": [
{
"track": "investor|buyer|technical",
"issue": "...",
"severity": "auto-fail|warn",
"suggested_fix": "..."
}
]
},
"objections": {
"need_response_update": [
{
"objection": "...",
"weighted_signal_count": 0,
"last_response_updated": "...",
"recommendation": "Update response - threshold reached"
}
],
"building": [
{
"objection": "...",
"weighted_signal_count": 0,
"note": "..."
}
],
"stable": 0
},
"overall_positioning_health": "good|needs_attention|critical"
}
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.
- 5d ago First seen · 113 lines · 19 tokens per session scan A 217ff9930881
06-positioning-check is an agent published in the GitHub repository assafkip/kipi-system (110 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 868 once invoked, about $0.0001 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 2026-09-03.
Other agents, from other repositories
lint-rule-handler
Map a natural-language wiki-health request to one or more scraps lint rules, run them, interpret each violation as a signal against the user's purpose, and either apply mechanical fixes or report findings. Use this agent for purpose-driven Scraps lint work.
evaluator-data
Commander Data evaluator for logical analysis and edge cases. Focus: logical consistency, edge cases, unintended consequences. Domain evaluator - invoked for technical and analytical tasks.
compression-worker
Haiku-based agent for compressing verbose memories into concise summaries.
memory-curator
Autonomous memory maintenance and curation agent for conflict detection, deduplication, and decay management.
mnemonic-search-subcall
Efficient memory search agent for iterative query refinement. Executes targeted ripgrep searches and returns structured findings.
evaluator-cto
Evaluates from CTO/technical perspective. Focus: technical accuracy, best practices, scalability. Core evaluator - always runs for every task.