Borrowing it
Nothing to install: this file belongs to senda-labs/DQIII8. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/senda-labs/DQIII8/main/.claude/skills/instinct-status/SKILL.mdgit clone --depth 1 https://github.com/senda-labs/DQIII8Wrote 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/senda-labs/dqiii8/instinct-status)<a href="https://agentmods.dev/skills/senda-labs/dqiii8/instinct-status"><img src="https://agentmods.dev/badge/skills/senda-labs/dqiii8/instinct-status/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/senda-labs/dqiii8/instinct-status"><img src="https://agentmods.dev/badge/skills/senda-labs/dqiii8/instinct-status.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 | $0.00028 | $0.00945 |
| Opus 5 | $0.00014 | $0.00473 |
| Sonnet 5 | $0.00006 | $0.00189 |
| Haiku 4.5 | $0.00003 | $0.00094 |
Grade A, and why
instinct-status 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 11d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/instinct-status — Instinct Status
Shows continuous learning instincts stored in dqiii8.db.
Usage
/instinct-status
/instinct-status --project dqiii8-core
/instinct-status --top 10
What it does
- Reads the
instinctstable fromdatabase/dqiii8.db - Groups by project (project-scoped first, then global)
- Shows confidence bar + times applied
- Highlights high-confidence instincts (>0.7) as "consolidated"
Implementation
python3 -c "
import sqlite3, os, sys
DB = 'database/dqiii8.db'
project_filter = None
top_n = 20
# Parse args (passed as ARGS env or argv)
args = sys.argv[1:]
for i, a in enumerate(args):
if a == '--project' and i+1 < len(args):
project_filter = args[i+1]
if a == '--top' and i+1 < len(args):
top_n = int(args[i+1])
conn = sqlite3.connect(DB)
if project_filter:
rows = conn.execute(
'SELECT keyword, pattern, confidence, times_applied, times_successful, project, created_at '
'FROM instincts WHERE project=? ORDER BY confidence DESC LIMIT ?',
(project_filter, top_n)
).fetchall()
else:
rows = conn.execute(
'SELECT keyword, pattern, confidence, times_applied, times_successful, project, created_at '
'FROM instincts ORDER BY project, confidence DESC LIMIT ?',
(top_n,)
).fetchall()
conn.close()
if not rows:
print('No instincts registered yet.')
print('They will be generated automatically at the end of sessions with corrections in tasks/lessons.md')
exit(0)
def conf_bar(c):
filled = int(c * 10)
return 'X' * filled + '.' * (10 - filled) + f' {int(c*100)}%'
print('=' * 60)
print(f' INSTINCT STATUS -- {len(rows)} total')
print('=' * 60)
current_proj = '__none__'
for kw, pattern, conf, applied, successful, proj, created in rows:
if proj != current_proj:
current_proj = proj
label = proj if proj else 'GLOBAL'
print(f'\n## {label.upper()}')
bar = conf_bar(conf or 0)
success_pct = int((successful or 0) / max(applied or 1, 1) * 100)
tag = ' consolidated' if (conf or 0) >= 0.7 else ''
print(f' {bar} [{kw}]{tag}')
print(f' applied: {applied or 0}x successful: {success_pct}% since: {(created or \"\")[:10]}')
if pattern:
preview = pattern[:80] + ('...' if len(pattern) > 80 else '')
print(f' {preview}')
"
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.
- 11d ago First seen · 118 lines · 28 tokens per session scan A 316addf2dabd
instinct-status is a skill published in the GitHub repository senda-labs/DQIII8 (11 stars, last pushed 22d ago), licensed MIT. It adds 28 tokens to every session and 945 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 2026-08-30.
Other skills, from other repositories
using-adaptive-harness
Auto-mode bootstrap for adaptive-harness. Intercepts tasks, routes to optimal harness, evaluates results. Use on every task when adaptive-harness auto-mode is active.
task-taxonomy
Reference for the 6-axis task taxonomy used by adaptive-harness routing. Use when user asks how tasks are classified.
harness-registry
Manage the adaptive-harness pool: list, inspect, promote, demote harnesses. Use when user asks about harness status or wants to manage the pool.
skill-review-response
Use when a reviewer, CI bot, or another AI leaves feedback to address.
sys-configure
Configure Claude Octopus — redirects to /octo:setup interactive wizard.
continuum-tools-mcp
Connect MCP servers (Stdio/SSE/StreamableHTTP) to a Continuum agent, configure tool filtering, set up tool-context capture/injection (e.g. sessionid), and read run artifacts (UI widgets, structured tool data). Invoke when the user asks "connect MCP", "filesystem tool", "remote API tool", "auto-capture sessionid"…