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 bnet47/codexicon --skill discovergit clone --depth 1 https://github.com/bnet47/codexiconWrote 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/bnet47/codexicon/discover)<a href="https://agentmods.dev/skills/bnet47/codexicon/discover"><img src="https://agentmods.dev/badge/skills/bnet47/codexicon/discover/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/bnet47/codexicon/discover"><img src="https://agentmods.dev/badge/skills/bnet47/codexicon/discover.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 | $0.00014 | $0.00479 |
| Opus 5.5 | $0.00006 | $0.00192 |
| Sonnet 5.5 | $0.00003 | $0.00096 |
| Haiku 4.5 | $0.00001 | $0.00048 |
Grade A, and why
discover scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Discover
Define or amend the durable project contract in the root SPEC.md without turning
ordinary discovery into an approval loop.
- Inspect the repository identity and any existing root
SPEC.mdandTASKS.md. - Ask only questions whose answers would materially change the product outcome, safety boundary, or irreversible technical direction. Batch related questions.
- Infer reversible details and record them as assumptions.
- Create or amend root
SPEC.mdin place with:- an observable outcome;
- stable requirement IDs such as
R-001; - interface contracts such as
I-001; - acceptance conditions such as
A-001; - explicit anti-goals covering what will not be built, mocked, or supported;
- assumptions and unresolved blockers.
- Keep requirements and interfaces append-only. Record changes under
Amendments; never silently rewrite or delete an existing contract item. Do not write only a brief or keep the active contract in transcript context. - Run
python scripts/codexicon.py spec-checkbefore continuing. If implementation is authorized and the change spans multiple tasks, create and validateTASKS.mdthrough$write-plan; if a register is absent,$autonomous-buildcreates the smallest traced register without another approval turn. - Continue directly to
$initor the shared$autonomous-buildloop when the request authorizes implementation. Use the persisted statesTODO,ACTIVE,BLOCKED, andDONE, with queue outcomesREADY,RESUME_ACTIVE,BLOCKED,COMPLETE, andINVALID.
Pure explanations and read-only reviews do not create or amend SPEC.md or TASKS.md and do not enter a code-generation workflow.
Build has one writer in the shared checkout: the primary agent by default. An explicitly chosen implementer may write one bounded task sequentially; the primary agent then re-reads the changed paths and owns integration and final verification. Never run concurrent writers.
Pause only for a critical unresolved domain decision, required credentials with no safe local substitute, or an unrecoverable repository/tooling failure. Do not ask for approval of routine wording or technical defaults. Do not commit or push.
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.
- 1mo ago Changed · +5 lines 68493da5ecfe
- 1mo ago Changed · -51 lines · -16 tokens per session 674beedfdd68
- 1mo ago First seen · 76 lines · 30 tokens per session scan A 0239f27b1b8d
discover is a skill published in the GitHub repository bnet47/codexicon (5 stars, last pushed 20d ago), licensed MIT. It adds 14 tokens to every session and 479 once invoked, about $0.0001 per session on Opus 5.5. 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
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
make_plan
For external plan request scenarios, guides the Agent to request a clear, actionable, step-by-step plan from a stronger Agent via listagents and chatwithagent, emphasizing that the plan is executed by the requester, not by the consulted Agent.
requirements-writer
Use when converting PM intake into a slice SPEC.md with observable acceptance outcomes, explicit scope, and advisory sibling build dependencies.
orchestration-team
Use when coordinating assignments, selected review boundaries, or blocked work across a rig.
oversight-team
Use when you are a seat on the oversight pod (a standing monitor-mode rig that keeps OTHER rigs healthy), configuring or running the drift detectors, or choosing whether to intervene vs escalate. Covers the pull-not-poll posture, the v0 detectors (premature-park, process-drift, off-task, token-burn), the intervention…
oma-scholar
Search academic literature and generate, validate, or compare Knows paper sidecars. Use for claim/evidence analysis and literature synthesis.