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 agentmods add skills/alicicek/tale-mode/tale-modenpx skills add alicicek/tale-mode --skill tale-modegit clone --depth 1 https://github.com/alicicek/tale-modeWrote 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/alicicek/tale-mode/tale-mode)<a href="https://agentmods.dev/skills/alicicek/tale-mode/tale-mode"><img src="https://agentmods.dev/badge/skills/alicicek/tale-mode/tale-mode.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 | $0.00098 | $0.07186 |
| Opus 5 | $0.00049 | $0.03593 |
| Sonnet 5 | $0.00020 | $0.01437 |
| Haiku 4.5 | $0.00010 | $0.00719 |
Grade B, and why
tale-mode scanned grade B with 2 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 6d 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.
`CLAUDE_CODE_STOP_HOOK_BLOCK_CAP` in `~/.claude/settings.json` (the loop is safe without it — Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
> browser/curl pass); §5 = `/code-review` on the diff (pass `<base>...<branch>`, no PR How it starts
The opening of the file, as written. The whole thing — 433 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tale Mode
What this is: a behavioral operating mode that changes how you approach hard work — it enforces the disciplines strong models skip when they rush. What this is not: it does not make the model smarter or close any raw-capability gap. It trades a little speed for correctness you can trust.
Platform note. Delegation (§3) and the independent review (§5) need a host that can spawn sub-agents (Claude Code and OpenAI Codex both can). On hosts that can't (e.g. the claude.ai app), run those strands sequentially yourself and do §5 as a deliberately hostile, fresh-frame self-review. Everything else applies as-is.
Phase pipeline (per host). For a large, multi-phase feature, drive it through the pipeline instead of one long session — it writes an approved plan decomposed into independently-shippable phases, then builds one phase per fresh session (enter plan mode, re-verify the plan against current code, wait for approval before editing). Claude Code: the slash commands
/tale-mode:plan-phase <feature>then/tale-mode:kickoff-phase <plan-file> <phase>. Codex (no user slash commands — skills are the trigger): the same two workflows ship as theplan-phase/kickoff-phaseskills — invoke them from the/skillspicker and name the plan-file + phase in your prompt./clear(CC) or a fresh session (Codex) between phases keeps context lean. Mention this for big multi-step work; skip it for single-session tasks.
Verification gate (per host). The §4 "run it and observe" and §5 review steps map to different tools per runtime — run the equivalent, never skip it. Claude Code: §4 =
/verify(did the change behave?) +/run(boot/drive the live app), picking what fits (pure logic →/verifyagainst a test; UI/API →/run+ a real browser/curl pass); §5 =/code-reviewon the diff (pass<base>...<branch>, no PR needed) and, for auth / money / secrets / storage,/security-review— both are bundled, model-invocable skills, invoked via the Skill tool. Codex: §4 = run the test / drive the app yourself and observe (there is no/verifyor/runskill); §5 routine = a free fresh-context sub-agent review (Codex can spawn one — frame it hostile), plus the bundledcodex-securityskills for auth / money / secrets / storage. Both hosts: a cross-model metered reviewer — Greptile, or the CodeRabbitcode-reviewskill on Codex — is the strongest §5 pass but is owner-triggered: never auto-run, comment@…, or push-loop it (each trigger costs real money). Surface it; let the owner spend it. The fresh-eyesplan-reviewercomplements the gate, never substitutes. Actually run the gate. A behavioral check that can't run yet (blocked on external provisioning — services, creds, infra) is a §0 deferral: log it in durable memory and treat the work as not-done until discharged, never skip it silently.
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.
- 6d ago First seen · 433 lines · 98 tokens per session scan B 91ff2826fcc9
tale-mode is a skill published in the GitHub repository alicicek/tale-mode (36 stars, last pushed 2mo ago), licensed MIT. It adds 98 tokens to every session and 7,186 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
recipe-front-review
Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.
recipe-reverse-engineer
Generate PRD and Design Docs from existing codebase through discovery, generation, verification, and review workflow.
new-skill
Scaffold a new brooks-lint analysis skill so it passes npm run validate and npm run evals on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (sequentially numbered steps), then appends…
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
brooks-test
Test quality review drawing on twelve classic engineering books — with primary focus on xUnit Test Patterns, The Art of Unit Testing, How Google Tests Software, and Working Effectively with Legacy Code — that diagnoses structural problems in an existing test suite: brittleness, mock abuse, coverage illusions, slow…
recipe-add-integration-tests
Add integration/E2E tests to existing codebase using Design Docs.