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/rennf93/opus-fable-playbookWrote 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/commands/rennf93/opus-fable-playbook/fable-status)<a href="https://agentmods.dev/commands/rennf93/opus-fable-playbook/fable-status"><img src="https://agentmods.dev/badge/commands/rennf93/opus-fable-playbook/fable-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/commands/rennf93/opus-fable-playbook/fable-status"><img src="https://agentmods.dev/badge/commands/rennf93/opus-fable-playbook/fable-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 | $0.00018 | $0.00483 |
| Opus 5 | $0.00009 | $0.00242 |
| Sonnet 5 | $0.00004 | $0.00097 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade B, and why
fable-status scanned grade B with 1 finding 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 9d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
1. Read `~/.claude/settings.json` (and `.claude/settings.local.json` if What it actually says
Report the current fable-mode posture. Steps:
- Read
~/.claude/settings.json(and.claude/settings.local.jsonif present). Report:outputStyle(is itFable?),model,effortLevel,alwaysThinkingEnabled. - Summarize hook drift telemetry by running:
python3 - <<'PY'
import calendar, json, os, time
path = os.environ.get("FABLE_TELEMETRY_FILE",
os.path.expanduser("~/.claude/fable-mode/telemetry.jsonl"))
cutoff = time.time() - 7 * 86400
counts = {}
try:
for line in open(path):
try:
e = json.loads(line)
ts = calendar.timegm(time.strptime(e["ts"], "%Y-%m-%dT%H:%M:%SZ"))
if ts >= cutoff:
key = (e["hook"], e["pattern"])
counts[key] = counts.get(key, 0) + 1
except Exception:
continue
except FileNotFoundError:
pass
if not counts:
print("no telemetry events in the last 7 days")
for (hook, pattern), n in sorted(counts.items(), key=lambda kv: -kv[1]):
print(f"{n:4d} {hook} {pattern}")
PY
- Interpret:
stop-gatecounts mean turn-discipline drift (doctrine §2);stop-gate-subagentcounts mean subagent turn-discipline drift (subagents returning intentions instead of findings);bash-disciplinemeans tool-discipline drift (§6);honesty-nudgefirings are informational (failures occurred and were flagged). - Report in prose, outcome first: overall posture, then the table framed
as the week's enforcement tax — each count is drift the plugin caught
that would otherwise have shipped — then which doctrine section (if
any) needs reinforcement per LOOP.md, then one line on how to disable
(
/plugin→ disable fable-mode; unsetoutputStyle).
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.
- 9d ago First seen · 48 lines · 18 tokens per session scan B 58b5fe23c44c
fable-status is a command published in the GitHub repository rennf93/opus-fable-playbook (34 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 483 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
decree
Issue a decree. Seats the organization on first use, then dispatches the teams.
report
The full account of the current decree — every figure verified before stated.
roster
Show the organization — roster, defect ledger, replacements, current cycle.
lore
Turn the lore on or off. Same organization, same rules — different register.
review
Verification review of a named agent's claim. Ends in acquittal or replacement.
recall-save
Generate / overwrite .recall/context.md with Recall's local offline summarizer.