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 Firstp1ck/pi-coding-agent-forge --skill repo-explorergit clone --depth 1 https://github.com/Firstp1ck/pi-coding-agent-forgeWrote 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/firstp1ck/pi-coding-agent-forge/repo-explorer)<a href="https://agentmods.dev/skills/firstp1ck/pi-coding-agent-forge/repo-explorer"><img src="https://agentmods.dev/badge/skills/firstp1ck/pi-coding-agent-forge/repo-explorer/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/firstp1ck/pi-coding-agent-forge/repo-explorer"><img src="https://agentmods.dev/badge/skills/firstp1ck/pi-coding-agent-forge/repo-explorer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 301 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00055 | $0.03203 |
| Opus 5.5 | $0.00022 | $0.01281 |
| Sonnet 5.5 | $0.00011 | $0.00641 |
| Haiku 4.5 | $0.00006 | $0.00320 |
Grade A, and why
repo-explorer 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.
How it starts
The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Explorer
When to Use
Activate this skill when:
- A caller agent needs to understand a repository before implementing, reviewing, or designing
- The task includes "explore", "map", "find where X is", "understand the codebase"
- The caller should NOT spend their own context window on raw file reads and searches
Workflow
Step 1: Parse the Request
The caller provides a request (natural language or structured). Extract:
- goal: What does the caller need to know? (e.g., "find the auth flow")
- target_paths: Which repo/directory to explore (absolute paths)
- depth:
shallow(structure only),standard(structure + key symbols),deep(full dependency tracing) - constraints: Any filters (language, directory scope, file patterns)
If the request is natural language, infer these fields before proceeding.
Step 2: Use the Native Tool for Routine Exploration
Call repo_explorer_explore first with budget: "compact" and includeEvidence: false unless the request already requires exact snippets. The native tool is the routine path: it refreshes or builds the index, performs budget-aware extraction, validates the handoff, writes the effectiveness report, and returns compact results in one agent-visible call.
Do not use Bash to preflight tool availability, refresh/build an index, run the helper sequence, or duplicate a successful native result. Tool availability is determined from the registered tool set. Bash is diagnostic-only after repo_explorer_explore is unavailable or an invocation fails; it is not an alternate routine exploration path.
When diagnosing a native failure, these helpers may reproduce the failing index stage:
python3 ./scripts/refresh_repo_index.py --repo "<target_path>" --data-dir data/
python3 ./scripts/build_repo_index.py --repo "<target_path>" --output data/<repo-name>-index.json
After diagnostics, report the native limitation or failure. Do not continue with broad shell exploration.
Step 3: Follow Up Only on Explicit Gaps
What ships with it
43 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- improve.md 13 KB
- scripts/benchmark_bash_usage.py 40 KB runs code
- scripts/build_repo_index.py 12 KB runs code
- scripts/extract_explorer_handoff.py 27 KB runs code
- scripts/refresh_repo_index.py 6.8 KB runs code
- scripts/summarize_effectiveness_reports.py 12 KB runs code
- scripts/validate_handoff.py 16 KB runs code
- tests/fixtures/bash-usage-corpus/manifest.json 5.9 KB
- tests/fixtures/bash-usage-corpus/repo/.env.example 46 B
- tests/fixtures/bash-usage-corpus/repo/.github/workflows/ci.yml 159 B
- tests/fixtures/bash-usage-corpus/repo/.gitignore 22 B
- tests/fixtures/bash-usage-corpus/repo/Cargo.toml 118 B
- tests/fixtures/bash-usage-corpus/repo/cmd/server/main.go 138 B
- tests/fixtures/bash-usage-corpus/repo/config/app.yaml 76 B
- tests/fixtures/bash-usage-corpus/repo/config/permissions.toml 113 B
- tests/fixtures/bash-usage-corpus/repo/docs/architecture.md 178 B
- tests/fixtures/bash-usage-corpus/repo/docs/security.md 175 B
- tests/fixtures/bash-usage-corpus/repo/go.mod 38 B
- tests/fixtures/bash-usage-corpus/repo/internal/router/router.go 143 B
- tests/fixtures/bash-usage-corpus/repo/package.json 130 B
- tests/fixtures/bash-usage-corpus/repo/pyproject.toml 145 B
- tests/fixtures/bash-usage-corpus/repo/README.md 227 B
- tests/fixtures/bash-usage-corpus/repo/scripts/check.sh 63 B runs code
- tests/fixtures/bash-usage-corpus/repo/src/javascript/audit.js 86 B runs code
- tests/fixtures/bash-usage-corpus/repo/src/javascript/legacy-auth.js 150 B runs code
- tests/fixtures/bash-usage-corpus/repo/src/python/acme/__init__.py 25 B runs code
- tests/fixtures/bash-usage-corpus/repo/src/python/acme/auth/__init__.py 71 B runs code
- tests/fixtures/bash-usage-corpus/repo/src/python/acme/auth/service.py 143 B runs code
- tests/fixtures/bash-usage-corpus/repo/src/python/acme/auth/token_store.py 102 B runs code
- tests/fixtures/bash-usage-corpus/repo/src/rust/auth.rs 114 B
- tests/fixtures/bash-usage-corpus/repo/src/rust/lib.rs 64 B
- tests/fixtures/bash-usage-corpus/repo/src/rust/session.rs 157 B
- tests/fixtures/bash-usage-corpus/repo/src/security/token_guard.py 137 B runs code
- tests/fixtures/bash-usage-corpus/repo/src/typescript/auth/authorization.ts 77 B runs code
- tests/fixtures/bash-usage-corpus/repo/src/typescript/auth/controller.ts 196 B runs code
- tests/fixtures/bash-usage-corpus/repo/src/typescript/auth/index.ts 127 B runs code
- tests/fixtures/bash-usage-corpus/repo/src/typescript/auth/session.ts 160 B runs code
- tests/fixtures/bash-usage-corpus/repo/tests/auth.test.ts 183 B runs code
- tests/fixtures/bash-usage-corpus/repo/tests/router_test.go 219 B
- tests/fixtures/bash-usage-corpus/repo/tests/test_auth.py 160 B runs code
- tests/fixtures/bash-usage-corpus/repo/tsconfig.json 106 B
- tests/test_bash_usage_benchmark.py 13 KB runs code
- tests/test_repo_explorer.py 26 KB runs code
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 First seen · 303 lines · 55 tokens per session scan A 03315c59c712
repo-explorer is a skill published in the GitHub repository Firstp1ck/pi-coding-agent-forge (91 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 3,203 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
convex-component-authoring
How to create, structure, and publish self-contained Convex components with proper isolation, exports, and dependency management.
npm-docs
Use this skill whenever the user asks about npm, package management, publishing packages, semantic versioning, npm CLI commands, or Node.js dependencies. Covers npm 12.x including the registry, scopes, organizations, security (audit, provenance, 2FA), CI/CD integration, workspaces, scripts, .npmrc configuration, and…
convex-component-authoring
How to create, structure, and publish self-contained Convex components with proper isolation, exports, and dependency management.
dependency-manager
Manage project dependencies — update packages, audit vulnerabilities, resolve conflicts, and keep dependencies healthy. Use when updating packages, fixing vulnerability alerts, or resolving dependency issues.
colab-finetuning
Fine-tune LLMs on Google Colab GPUs directly from openscience. Connects to Colab runtimes via WebSocket bridge for remote training with Unsloth. Supports SFT, GRPO, DPO, vision, and TTS workflows on free T4 to Pro A100 GPUs.
swarm-pr-review
Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…